# Pp Fec > Printing Press CLI for Fec. This application programming interface (API) - Skill: `mvanhorn-printing-press-libra/pp-fec` (Agent Skill) - Install (CLI): `npx skillmds add mvanhorn-printing-press-libra/pp-fec` - Raw SKILL.md: https://api.skillmd.com/api/skills/mvanhorn-printing-press-libra/pp-fec/raw - Safety review: pending - Works with: Claude Code, Claude.ai, OpenAI Codex - Category: Integrations & APIs - License: Apache-2.0 - Author: mvanhorn (https://skillmd.com/u/mvanhorn-printing-press-libra) - Updated: 2026-09-09 - Page: https://skillmd.com/skills/mvanhorn-printing-press-libra/pp-fec --- # Fec — Printing Press CLI ## Prerequisites: Install the CLI This skill drives the `fec-pp-cli` binary. **You must verify the CLI is installed before invoking any command from this skill.** If it is missing, install it first: 1. Install via the Printing Press installer. It defaults binaries to `$HOME/.local/bin` on macOS/Linux and `%LOCALAPPDATA%\Programs\PrintingPress\bin` on Windows: ```bash npx -y @mvanhorn/printing-press-library install fec --cli-only ``` 2. Verify: `fec-pp-cli --version` 3. Ensure the reported install directory is on `$PATH` for the agent/runtime that will invoke this skill. If the `npx` install fails (no Node, offline, etc.), fall back to a direct Go install (requires Go 1.26.6 or newer). This installs into `$GOPATH/bin` (default `$HOME/go/bin`), so add that directory to `$PATH` instead: ```bash go install github.com/mvanhorn/printing-press-library/library/other/fec/cmd/fec-pp-cli@latest ``` If `--version` reports "command not found" after install, the runtime cannot see the binary directory on `$PATH`. Do not proceed with skill commands until verification succeeds. This application programming interface (API) allows you to explore the way candidates and committees fund their campaigns. The Federal Election Commission (FEC) API is a RESTful web service supporting full-text and field-specific searches on FEC data. [Bulk downloads](https://www.fec.gov/data/advanced/?tab=bulk-data) are available on the current site. Information is tied to the underlying forms by file ID and image ID. Data are updated nightly. There are a lot of data, and a good place to start is to use search to find interesting candidates and committees. Then, you can use their IDs to find report or line item details with the other endpoints. If you are interested in individual donors, check out contributor information in the `/schedule_a/` endpoints. Getting started with the openFEC API
If you would like to use the FEC's API programmatically, you can sign up for your own API key using our form. Alternatively, you can still try out our API without an API key by using the web interface and using DEMO_KEY. Note that when you use the openFEC API you are subject to the [Terms of Service](https://github.com/fecgov/FEC/blob/master/TERMS-OF-SERVICE.md) and [Acceptable Use policy](https://github.com/fecgov/FEC/blob/master/ACCEPTABLE-USE-POLICY.md). Signing up for an API key will enable you to place up to 1,000 calls an hour. Each call is limited to 100 results per page. You can email questions, comments or a request to get a key for 7,200 calls an hour (120 calls per minute) to APIinfo@fec.gov. You can also ask questions and discuss the data in a community led [group](https://groups.google.com/forum/#!forum/fec-data). The model definitions and schema are available at [/swagger](/swagger/). This is useful for making wrappers and exploring the data. A few restrictions limit the way you can use FEC data. For example, you can’t use contributor lists for commercial purposes or to solicit donations. [Learn more here](https://www.fec.gov/updates/sale-or-use-contributor-information/). [Inspect our source code](https://github.com/fecgov/openFEC). We welcome issues and pull requests!


Sign up for an API key

Loading signup form...
## When Not to Use This CLI Do not activate this CLI for requests that require creating, updating, deleting, publishing, commenting, upvoting, inviting, ordering, sending messages, booking, purchasing, or changing remote state. This printed CLI exposes read-only commands for inspection, export, sync, and analysis. ## Command Reference **audit-case** — Manage audit case - `fec-pp-cli audit-case` — This endpoint contains Final Audit Reports approved by the Commission since inception. **audit-category** — Manage audit category - `fec-pp-cli audit-category` — This lists the options for the categories and subcategories available in the /audit-search/ endpoint. **audit-primary-category** — Manage audit primary category - `fec-pp-cli audit-primary-category` — This lists the options for the primary categories available in the /audit-search/ endpoint. **calendar-dates** — Manage calendar dates - `fec-pp-cli calendar-dates list` — Combines the election and reporting dates with Commission meetings, conferences, outreach, Advisory Opinions, rules - `fec-pp-cli calendar-dates list-calendardates` — Returns CSV or ICS for downloading directly into calendar applications like Google, Outlook or other applications. **candidate** — Candidate endpoints give you access to information about the people running for office. This information is organized by `candidate_id`. If you're unfamiliar with candidate IDs, using `/candidates/search/` will help you locate a particular candidate. Officially, a candidate is an individual seeking nomination for election to a federal office. People become candidates when they (or agents working on their behalf) raise contributions or make expenditures that exceed $5,000. The candidate endpoints primarily use data from FEC registration [Form 1](https://www.fec.gov/resources/cms-content/documents/fecfrm1.pdf) for committee information and [Form 2](https://www.fec.gov/resources/cms-content/documents/fecfrm2.pdf) for candidate information. - `fec-pp-cli candidate` — This endpoint is useful for finding detailed information about a particular candidate. **candidates** — Candidate endpoints give you access to information about the people running for office. This information is organized by `candidate_id`. If you're unfamiliar with candidate IDs, using `/candidates/search/` will help you locate a particular candidate. Officially, a candidate is an individual seeking nomination for election to a federal office. People become candidates when they (or agents working on their behalf) raise contributions or make expenditures that exceed $5,000. The candidate endpoints primarily use data from FEC registration [Form 1](https://www.fec.gov/resources/cms-content/documents/fecfrm1.pdf) for committee information and [Form 2](https://www.fec.gov/resources/cms-content/documents/fecfrm2.pdf) for candidate information. - `fec-pp-cli candidates list` — Fetch basic information about candidates, and use parameters to filter results to the candidates you're looking for. - `fec-pp-cli candidates list-search` — Fetch basic information about candidates and their principal committees. Each result reflects a unique FEC candidate ID. - `fec-pp-cli candidates list-totals` — Aggregated candidate receipts and disbursements grouped by cycle. - `fec-pp-cli candidates list-totals-2` — Candidate total receipts and disbursements aggregated by `aggregate_by`. **committee** — Committees are entities that spend and raise money in an election. Their characteristics and relationships with candidates can change over time. You might want to use filters or search endpoints to find the committee you're looking for. Then you can use other committee endpoints to explore information about the committee that interests you. Financial information is organized by `committee_id`, so finding the committee you're interested in will lead you to more granular financial information. The committee endpoints include all FEC filers, even if they aren't registered as a committee. Officially, committees include the committees and organizations that file with the FEC. Several different types of organizations file financial reports with the FEC: *Campaign committees authorized by particular candidates to raise and spend funds in their campaigns. Non-party committees (e.g., PACs), some of which may be sponsored by corporations, unions, trade or membership groups, etc. Political party committees at the national, state, and local levels. Groups and individuals making only independent expenditures Corporations, unions, and other organizations making internal communications* The committee endpoints primarily use data from FEC registration Form 1 and Form 2. - `fec-pp-cli committee ` — This endpoint is useful for finding detailed information about a particular committee or filer. **committees** — Committees are entities that spend and raise money in an election. Their characteristics and relationships with candidates can change over time. You might want to use filters or search endpoints to find the committee you're looking for. Then you can use other committee endpoints to explore information about the committee that interests you. Financial information is organized by `committee_id`, so finding the committee you're interested in will lead you to more granular financial information. The committee endpoints include all FEC filers, even if they aren't registered as a committee. Officially, committees include the committees and organizations that file with the FEC. Several different types of organizations file financial reports with the FEC: *Campaign committees authorized by particular candidates to raise and spend funds in their campaigns. Non-party committees (e.g., PACs), some of which may be sponsored by corporations, unions, trade or membership groups, etc. Political party committees at the national, state, and local levels. Groups and individuals making only independent expenditures Corporations, unions, and other organizations making internal communications* The committee endpoints primarily use data from FEC registration Form 1 and Form 2. - `fec-pp-cli committees` — Fetch basic information about committees and filers. Use parameters to filter for particular characteristics. **communication-costs** — Reports of communication costs by corporations and membership organizations from the FEC [F7 forms](https://www.fec.gov/pdf/forms/fecform7.pdf). - `fec-pp-cli communication-costs list` — 52 U.S.C. - `fec-pp-cli communication-costs list-communicationcosts` — Communication cost aggregated by candidate ID and committee ID. - `fec-pp-cli communication-costs list-communicationcosts-2` — Communication cost aggregated by candidate ID and committee ID. - `fec-pp-cli communication-costs list-communicationcosts-3` — Total communications costs aggregated across committees on supported or opposed candidates by cycle or candidate **efile** — Manage efile - `fec-pp-cli efile list` — Basic information about electronic files coming into the FEC, posted as they are received. - `fec-pp-cli efile list-form1` — Basic information about electronic files coming into the FEC, posted as they are received. - `fec-pp-cli efile list-form2` — Basic information about electronic files coming into the FEC, posted as they are received. - `fec-pp-cli efile list-reports` — Key financial data reported periodically by committees as they are reported. - `fec-pp-cli efile list-reports-2` — Key financial data reported periodically by committees as they are reported. - `fec-pp-cli efile list-reports-3` — Key financial data reported periodically by committees as they are reported. **election-dates** — Manage election dates - `fec-pp-cli election-dates` — FEC election dates since 1995. **electioneering** — An electioneering communication is any broadcast, cable or satellite communication that fulfills each of the following conditions: _The communication refers to a clearly identified federal candidate._ _The communication is publicly distributed by a television station, radio station, cable television system or satellite system for a fee._ _The communication is distributed within 60 days prior to a general election or 30 days prior to a primary election to federal office._ - `fec-pp-cli electioneering list` — An electioneering communication is any broadcast - `fec-pp-cli electioneering list-aggregates` — Electioneering communications costs aggregates - `fec-pp-cli electioneering list-bycandidate` — Electioneering costs aggregated by candidate - `fec-pp-cli electioneering list-totals` — Total electioneering communications spent on candidates by cycle or candidate election year **elections** — Manage elections - `fec-pp-cli elections list` — Look at the top-level financial information for all candidates running for the same office. - `fec-pp-cli elections list-search` — List elections by cycle, office, state, and district. - `fec-pp-cli elections list-summary` — List elections by cycle, office, state, and district. **filings** — All official records and reports filed by or delivered to the FEC. Note: because the filings data includes many records, counts for large result sets are approximate; you will want to page through the records until no records are returned. - `fec-pp-cli filings` — All official records and reports filed by or delivered to the FEC. **legal** — Explore relevant statutes, regulations and Commission actions. - `fec-pp-cli legal get` — Search legal documents by type and number - `fec-pp-cli legal list` — Search legal documents by document type, or across all document types using keywords, parameter values and ranges. **names** — Manage names - `fec-pp-cli names list` — Search for candidates or committees by name. - `fec-pp-cli names list-auditcommittees` — Search for candidates or committees by name. - `fec-pp-cli names list-candidates` — Search for candidates or committees by name. - `fec-pp-cli names list-committees` — Search for candidates or committees by name. **national-party** — Manage national party - `fec-pp-cli national-party list` — This endpoint includes national party committee account receipts for presidential nominating conventions - `fec-pp-cli national-party list-nationalparty` — This endpoint includes national party committee account disbursements for presidential nominating conventions - `fec-pp-cli national-party list-nationalparty-2` — This endpoint includes national party committee account total receipts and total disbursements for presidential **operations-log** — Manage operations log - `fec-pp-cli operations-log` — The Operations log contains details of each report loaded into the database. **presidential** — Data supporting fec.gov's presidential map. For more information about the presidential map data available to download from fec.gov, please visit: https://www.fec.gov/campaign-finance-data/presidential-map-data/ - `fec-pp-cli presidential list` — Coverage end date per candidate. Filter by candidate_id and/or election_year - `fec-pp-cli presidential list-contributions` — Net receipts per candidate. Filter with `contributor_state='US'` for national totals - `fec-pp-cli presidential list-contributions-2` — Contribution receipts by size per candidate. Filter by candidate_id, election_year and/or size - `fec-pp-cli presidential list-contributions-3` — Contribution receipts by state per candidate. Filter by candidate_id and/or election_year - `fec-pp-cli presidential list-financialsummary` — Financial summary per candidate. Filter by candidate_id and/or election_year **rad-analyst** — Manage rad analyst - `fec-pp-cli rad-analyst` — Use this endpoint to look up the RAD Analyst for a committee. **reporting-dates** — Manage reporting dates - `fec-pp-cli reporting-dates` — FEC election dates since 1995. **reports** — Manage reports - `fec-pp-cli reports` — Each report represents the summary information from Form 3, Form 3X and Form 3P. **rulemaking** — Manage rulemaking - `fec-pp-cli rulemaking` — The Searchable Electronic Rulemaking System (SERS) **schedules** — Manage schedules - `fec-pp-cli schedules get` — This description is for both ​`/schedules​/schedule_a​/` and ​ `/schedules​/schedule_a​/{sub_id}​/`. - `fec-pp-cli schedules get-scheduleb` — Schedule B filings describe itemized disbursements. - `fec-pp-cli schedules get-schedulec` — Schedule C shows all loans, endorsements and loan guarantees a committee receives or makes. - `fec-pp-cli schedules get-scheduled` — Schedule D, it shows debts and obligations owed to or by the committee that are required to be disclosed. - `fec-pp-cli schedules get-schedulef` — Schedule F - `fec-pp-cli schedules list` — This description is for both ​`/schedules​/schedule_a​/` and ​ `/schedules​/schedule_a​/{sub_id}​/`. - `fec-pp-cli schedules list-schedulea` — This endpoint provides itemized individual contributions received by a committee - `fec-pp-cli schedules list-schedulea-10` — Itemized individual contributions aggregated by contributor’s state, candidate, committee type and cycle. - `fec-pp-cli schedules list-schedulea-2` — This endpoint provides itemized individual contributions received by a committee - `fec-pp-cli schedules list-schedulea-3` — This endpoint provides individual contributions received by a committee, aggregated by size - `fec-pp-cli schedules list-schedulea-4` — This endpoint provides itemized individual contributions received by a committee, aggregated by the contributor’s state. - `fec-pp-cli schedules list-schedulea-5` — This endpoint provides itemized individual contributions received by a committee - `fec-pp-cli schedules list-schedulea-6` — Efiling endpoints provide real-time campaign finance data received from electronic filers. - `fec-pp-cli schedules list-schedulea-7` — This endpoint provides itemized individual contributions received by a committee - `fec-pp-cli schedules list-schedulea-8` — This endpoint provides itemized individual contributions received by a committee - `fec-pp-cli schedules list-schedulea-9` — This endpoint provides itemized individual contributions received by a committee, aggregated by contributor’s state - `fec-pp-cli schedules list-scheduleaform5` — FEC FORM 5 Receipts REPORT OF INDEPENDENT EXPENDITURES MADE AND CONTRIBUTIONS RECEIVED To Be Used By Persons (Other - `fec-pp-cli schedules list-scheduleb` — Schedule B filings describe itemized disbursements. - `fec-pp-cli schedules list-scheduleb-2` — Schedule B disbursements aggregated by disbursement purpose category. - `fec-pp-cli schedules list-scheduleb-3` — Schedule B disbursements aggregated by recipient name. To avoid double counting, memoed items are not included. - `fec-pp-cli schedules list-scheduleb-4` — Schedule B disbursements aggregated by recipient committee ID, if applicable. - `fec-pp-cli schedules list-scheduleb-5` — Efiling endpoints provide real-time campaign finance data received from electronic filers. - `fec-pp-cli schedules list-schedulec` — Schedule C shows all loans, endorsements and loan guarantees a committee receives or makes. - `fec-pp-cli schedules list-scheduled` — Schedule D, it shows debts and obligations owed to or by the committee that are required to be disclosed. - `fec-pp-cli schedules list-schedulee` — Schedule E covers the line item expenditures for independent expenditures. - `fec-pp-cli schedules list-schedulee-2` — Schedule E receipts aggregated by recipient candidate. To avoid double counting, memoed items are not included. - `fec-pp-cli schedules list-schedulee-3` — Efiling endpoints provide real-time campaign finance data received from electronic filers. - `fec-pp-cli schedules list-schedulee-4` — Total independent expenditure on supported or opposed candidates by cycle or candidate election year. - `fec-pp-cli schedules list-schedulef` — Schedule F - `fec-pp-cli schedules list-scheduleh4` — Schedule H4 filings describe disbursements for allocated federal/nonfederal activity. - `fec-pp-cli schedules list-scheduleh4-2` — Efiling endpoints provide real-time campaign finance data received from electronic filers. **state-election-office** — Manage state election office - `fec-pp-cli state-election-office` — State laws and procedures govern elections for state or local offices as well as how candidates appear on election **totals** — Manage totals - `fec-pp-cli totals get` — This endpoint provides information about a committee's Form 3, Form 3X, or Form 3P financial reports - `fec-pp-cli totals list` — Provides cumulative receipt totals by entity type, over a two year cycle. Totals are adjusted to avoid double counting. - `fec-pp-cli totals list-inauguralcommittees` — This endpoint provides information about an inaugural committee's Form 13 report of donations accepted. ### Finding the right command When you know what you want to do but not which command does it, ask the CLI directly: ```bash fec-pp-cli which '' ``` `which` resolves a natural-language capability query to the best matching command from this CLI's curated feature index. Exit code `0` means at least one match; exit code `2` means no confident match — fall back to `--help` or use a narrower query. ## Auth Setup Run `fec-pp-cli auth setup` to print the URL and steps for getting a key (add `--launch` to open the URL). Then set: ```bash export FEC_API_KEY_QUERY_AUTH="" ``` To persist credentials, use `fec-pp-cli auth set-token `. Stored secrets live in `credentials.toml` under the data dir, not in `config.toml`. Run `fec-pp-cli doctor` to verify setup. ## Agent Mode Add `--agent` to any command. Expands to: `--json --compact --no-input --no-color --yes`. - **Pipeable** — JSON on stdout, errors on stderr - **Filterable** — `--select` keeps a subset of fields. Dotted paths descend into nested structures; arrays traverse element-wise. Critical for keeping context small on verbose APIs: ```bash fec-pp-cli audit-case --agent --select id,name,status ``` - **Previewable** — `--dry-run` shows the request without sending - **Offline-friendly** — sync/search commands can use the local SQLite store when available - **Non-interactive** — never prompts, every input is a flag - **Read-only** — do not use this CLI for create, update, delete, publish, comment, upvote, invite, order, send, or other mutating requests ### Response envelope Commands that read from the local store or the API wrap output in a provenance envelope: ```json { "meta": {"source": "live" | "local", "synced_at": "...", "reason": "..."}, "results": } ``` Parse `.results` for data and `.meta.source` to know whether it's live or local. A human-readable `N results (live)` summary is printed to stderr only when stdout is a terminal AND no machine-format flag (`--json`, `--csv`, `--compact`, `--quiet`, `--plain`, `--select`) is set — piped/agent consumers and explicit-format runs get pure JSON on stdout. ## Paths and state Agents should treat the CLI's path resolver as part of the runtime contract: - Use `--home ` for one invocation, or set `FEC_HOME=` to relocate all four path kinds under one root. - Use per-kind env vars only when a specific kind must diverge: `FEC_CONFIG_DIR`, `FEC_DATA_DIR`, `FEC_STATE_DIR`, `FEC_CACHE_DIR`. - Resolution order is per-kind env var, `--home`, `FEC_HOME`, XDG (`XDG_CONFIG_HOME`, `XDG_DATA_HOME`, `XDG_STATE_HOME`, `XDG_CACHE_HOME`), then platform defaults. - `config` contains settings like `config.toml` and profiles. `data` contains `credentials.toml`, `data.db`, cookies, and auth sidecars. `state` contains persisted queries, jobs, and `teach.log`. `cache` contains regenerable HTTP/cache files. - Stored secrets live in `credentials.toml` under the data dir. Existing legacy `config.toml` secrets are read for compatibility and leave `config.toml` on the first auth write. - Run `fec-pp-cli doctor --fail-on warn` to surface path and credential-location warnings. `agent-context` exposes a schema v4 `paths` block for agents that need the resolved dirs. - For MCP, pass relocation through the MCP host config. The MCP binary does not inherit CLI flags: ```json { "mcpServers": { "fec": { "command": "fec-pp-mcp", "env": { "FEC_HOME": "/srv/fec" } } } } ``` Fleet precedence: an inherited per-kind env var overrides an explicit `--home` for that kind. Use `FEC_HOME` or per-kind vars as durable fleet levers, and use `--home` only for a single invocation. Relocation is not reversible by unsetting env vars; move files manually before clearing `FEC_HOME`, or `doctor` will not find credentials left under the former root. ## Automatic learning This CLI ships a self-capturing learning loop. The CLI does its own bookkeeping: every invocation is journaled locally, a failed flag followed by a corrected retry auto-derives a `flag_alias` candidate, and a `teach` on a query family without a playbook auto-synthesizes a `playbook_candidate` from the session's journal. Your job is judgment only: `recall` first, act on surfaced candidates, `teach` the final answer, `playbook amend` when you observe a correction. You never record failures by hand. ### Step 1: `recall` before any discovery Before list/search/drill commands on a new user question, run: ```bash fec-pp-cli recall '' --agent ``` The response envelope: ```json { "query": "...", "normalized": "", "query_entities": ["..."], "found": true | false, "match_score": 0.0, "results": [ { "resource_id": "...", "resource_type": "...", "venue": "...", "confidence": 2, "entity_match": "exact|partial|unknown", "source": "taught|preseed|pattern", "warnings": ["..."] } ], "mismatches": [ /* only when --debug-mismatches */ ], "warnings": [ /* top-level */ ], "candidates": [ { "id": 12, "class": "flag_alias | playbook_candidate", "summary": "...", "sightings": 3, "last_seen": "...", "rationale": "...", "next_action": ["", "fec-pp-cli learnings confirm 12"] } ], "playbook": { "query_family": "...", "playbook": { "steps": [ { "cmd": "", "purpose": "..." } ], "entity_slots": ["$ENTITY"], "expected_tool_calls": 3 }, "slots_resolved": { "$ENTITY": { "token": "", "canonical": "" } }, "notes": "" }, "notes": "" } ``` Empty-store short-circuit: if the store has no learnings, playbooks, or candidates yet (recall finds nothing and `learnings list` and `learnings candidates` are both empty), skip recall for the rest of this session instead of taxing every query; resume recall-first once something has been taught. ### Step 2: decision tree Read `candidates`, `playbook`, `notes`, `results[0]`, and warnings in that order: ``` if Candidates present (warnings include "candidates_present"): -> candidates are try-then-confirm, never facts. Follow each candidate's two-step next_action verbatim: run the trial command first, then run `learnings confirm ` only after the trial verified the behavior. Reject a wrong candidate with `learnings reject `. -> NEVER re-teach something recall surfaced as a candidate; confirm or reject that candidate instead of teaching a duplicate. -> candidates ride alongside playbooks and resource hits, not instead of them; continue with the branches below after acting on them. if Playbook present: -> READ Playbook.notes verbatim FIRST (workarounds + gotchas the CLI surface doesn't expose) -> replay Playbook.steps in order, substituting Playbook.slots_resolved entries for the entity slot tokens. If a step's slot is unresolved, fall back to discovery for that step only. -> the Playbook's expected_tool_calls is a budget; if you find yourself running materially more, record the divergence via `fec-pp-cli playbook amend` at end-of-session. elif Notes present (no Playbook): -> read Notes verbatim before any discovery step; they carry known gotchas for this query family even when no structured choreography exists yet. elif Found AND Results[0].EntityMatch == "exact" AND Results[0].Confidence >= 2: -> skip discovery; fetch live data for Results[*].ResourceID in parallel elif Found AND Results[0].EntityMatch == "partial": -> candidate hint, NOT a hit; read the resource title to validate before trusting elif (any row in Mismatches[] when --debug-mismatches was passed): -> treat as cold start; the stored learning is for a different entity (different canonical resolved from query_entities) else: // Found == false, no playbook, no notes -> cold start; run discovery normally; teach the answer afterward (Step 4). If the family has no playbook yet, that teach auto-synthesizes a playbook candidate from this session's journal - you do not need to record one by hand. ``` Playbook and Notes are orthogonal to the per-resource path. A recall response can carry both a Playbook AND a `Results[]` hit - use both: the Playbook tells you which choreography to run; the resource hits short-circuit specific steps. Default to skipping `mismatches`; pass `--debug-mismatches` only when investigating cold-start surprises. Candidate judgment details: `learnings confirm ` prints the candidate's full payload before materializing it - check that the printed payload matches the behavior you verified. `learnings reject ` tombstones the derivation signature so the same candidate does not resurface. The envelope carries only the few candidates worth acting on now; `fec-pp-cli learnings candidates` lists the full open set. Graceful degradation: if `learnings confirm` is an unknown command, you are driving an older binary - ignore the candidates guidance and follow the rest of the protocol. ### Step 3: always read `warnings` - `low_confidence`: row exists at `confidence<2`. Treat as a hint, not a skip-discovery hit. - `resource_not_in_store`: the local store doesn't have the resource the learning points at. The match validator couldn't classify entities — direct-fetch and re-evaluate. - `cross_alias_match` (per-result): the row was taught under a different alias and matched the live query's canonical via `entity_lookups` (e.g., a "USA" teach satisfying a "United States" recall). Trust the resource_id. - `similar_shape_different_entity:` (top-level): a structurally matching row exists but its canonical entity differs from the live query's. Treated as cold start; the warning carries the conflicting canonical as a hint, but the row is NOT promoted into Results. - `ambiguous_alias` (top-level): a single query entity resolved to multiple canonicals (e.g., "Cards" → Arizona Cardinals + St. Louis Cardinals). Surface the ambiguity from context before committing to a resource. - `candidates_present` (top-level): the envelope carries a `candidates` section. Handle it via the candidates branch in Step 2 before anything else. - `lookup_refresh_available` (top-level): an entity in the query has no lookup row yet, but synced data could provide one. Run `fec-pp-cli sync` to refresh entity lookups. - Top-level `no_learnings_for_query_family`: the table had no rows above the Jaccard floor. Pure cold start. ### Step 4: `teach &` after finalizing your response - always Teaching is unconditional. After resolving a query the store could not answer, background-teach the final resource mapping - no call-count threshold, no judging whether it was "worth" learning. The teach is the anchor of the loop: it triggers playbook synthesis for a family without a playbook, and same-referent phrasings fold into one family so near-duplicate teaches do not fragment the store. Fire it after assembling your user-facing response but BEFORE emitting it, with a shell `&` so the call returns immediately: ```bash fec-pp-cli teach --query '' --resource-type --resource --resource # (append shell `&` to background it) ``` Quoting rule: never interpolate the user's question into a double-quoted shell string - command substitutions inside would execute with your local privileges when the shell expands it. Single-quote the whole argument (escape inner single quotes as `'''`) or pass the question via your harness's argument-array/stdin mechanism instead of a shell string. This applies to every teach-family command that takes user-derived text (`teach`, `teach-playbook`, `playbook amend`). Silent on success. Errors only land in `teach.log` under the resolved state dir. Teach the **most specific** resource - if the user asked a broad question and you walked through parent records to find the specific answer, teach the leaf id, not the parent. The CLI uses seeded `entity_lookups` for cross-alias resolution at recall time, so a teach under one alias (e.g., "Niners") satisfies future queries under another alias (e.g., "49ers", "San Francisco") automatically. PII rule: teach the structural question with identifiers stripped - never include names, emails, phone numbers, account ids, or other personal identifiers in taught queries or notes. The CLI scans teach queries for obvious email/phone shapes and warns, but does not block; strip before teaching rather than relying on the warning. ### Step 5: playbooks - optional flags, automatic synthesis You do not need to decide whether a session "deserves" a playbook: a teach on a family without one auto-synthesizes a `playbook_candidate` from the session's journal, and the next session judges it via confirm/reject. Attach explicit playbook flags only when you already hold choreography worth recording verbatim - workarounds the CLI didn't surface (silently-dropped flags, undocumented params, pagination tricks, payload gotchas). Prefer the **integrated one-call form** - record the resource learning and the playbook in the same `teach` invocation: ```bash # Common case: record both the resource learning AND the playbook in one call. fec-pp-cli teach \ --query '' \ --resource \ --playbook-file ~/playbooks/.json \ --playbook-notes-file ~/playbooks/-notes.md # (append shell `&` to background it) # Alternate: playbook-only (no resource to record alongside). fec-pp-cli teach-playbook \ --query '' \ --playbook-file ~/playbooks/.json \ --notes-file ~/playbooks/-notes.md ``` Playbook files are JSON with `steps`, `entity_slots`, `expected_tool_calls`. Notes files are markdown carrying the gotchas verbatim. File-free callers (MCP-only agents) pass the same content inline: `--playbook-json` and `--playbook-notes` on the integrated `teach` form, `--playbook-json` and `--notes` on `teach-playbook`. On the integrated `teach` form, the playbook flags are optional - omit them entirely for a resource-only teach. On the standalone `teach-playbook` form, at least one of the playbook and notes flags must be set; both empty is rejected. Playbooks are keyed on the structural query family (entities stripped) so a recipe taught from one entity-shaped query applies to every other query of the same shape, with `slots_resolved` binding the live query's canonical at recall time. When you DO find a playbook on a future recall, treat it as ground truth: replay the steps with `slots_resolved` substitutions, skip the discovery that the choreography already documents, and read `notes` before any step. ### Step 6: `playbook amend &` when your debug response identifies a correction If your debug-protocol response identifies a concrete correction the notes or playbook should know — a workaround, an undocumented endpoint shape, a stale field name, observed schema drift, an empty-payload fallback — fire `playbook amend` BEFORE emitting your user-facing response. Same fire-and-forget posture as `teach`. ```bash fec-pp-cli playbook amend \ --query '' \ --add-note '' # (append shell `&` to background it) ``` What counts as worth amending: a behavior you OBSERVED this session that future-you would benefit from knowing. Examples worth amending: - A workaround for a CLI surface that silently drops or misorders a flag. - An undocumented endpoint shape (response wrapped in `{meta, results}`, payload nested two levels deeper than the docs claim). - Observed schema drift (a field renamed, an index that shifted between seasons, a category label that the API now returns lower-cased). What does NOT belong in notes: - The year-specific or entity-specific answer to the user's question. That's the response, not a learning. - Per-team / per-athlete / per-row data the playbook already retrieves at runtime. - Statements that paraphrase what the existing notes already say. The amend command appends to the family's existing notes with a timestamped marker (`[amend YYYY-MM-DDTHH:MMZ]: `). Multiple amends accumulate; the audit trail is visible. If no playbook exists yet for the family, amend creates a notes-only one (so cold-start corrections still land). #### PII discipline for amend notes `playbook amend` notes are designed to potentially flow upstream as shared knowledge in future versions of the Printing Press. Keep them clean of user-identifying content so the upstream-contribution path stays open without retroactive scrubbing: - **Do NOT embed** paths to user filesystems, personal API keys or tokens, user email addresses, user GitHub handles, or specific query histories tied to a single user. - **Acceptable**: endpoint shapes, undocumented field names, API gotchas, observed schema drift, workarounds for CLI surfaces, generalizable pagination or retry tactics. If a correction is only meaningful with user-specific context, it belongs in a personal note, not in the playbook amend. ### Measuring the loop `fec-pp-cli learnings stats` reports recall hit rate, teach-to-reuse, playbook resolution rate, and candidate confirm/reject counts from the local `learn_events` table. Rates are null until they have a denominator; everything stays on this machine. Use it to check whether the loop is earning its keep for this CLI. ### Disabling learning - `--no-learn` on a single command short-circuits both `recall` and the `teach` write path. Use for deterministic agent flows or tests that must not be affected by accumulated learnings. - `FEC_NO_LEARN=true` in the environment globally disables the pipeline. ## Agent Feedback When you (or the agent) notice something off about this CLI, record it: ``` fec-pp-cli feedback "the --since flag is inclusive but docs say exclusive" fec-pp-cli feedback --stdin < notes.txt fec-pp-cli feedback list --json --limit 10 ``` Entries are stored locally as `feedback.jsonl` under the resolved data dir. They are never POSTed unless `FEC_FEEDBACK_ENDPOINT` is set AND either `--send` is passed or `FEC_FEEDBACK_AUTO_SEND=true`. Default behavior is local-only. Write what *surprised* you, not a bug report. Short, specific, one line: that is the part that compounds. ## Output Delivery Every command accepts `--deliver `. The output goes to the named sink in addition to (or instead of) stdout, so agents can route command results without hand-piping. Three sinks are supported: | Sink | Effect | |------|--------| | `stdout` | Default; write to stdout only | | `file:` | Atomically write output to `` (tmp + rename) | | `webhook:` | POST the output body to the URL (`application/json` or `application/x-ndjson` when `--compact`) | Unknown schemes are refused with a structured error naming the supported set. Webhook failures return non-zero and log the URL + HTTP status on stderr. ## Named Profiles A profile is a saved set of flag values, reused across invocations. Use it when a scheduled or recurring agent reuses the same saved flags while providing different input each run. ``` fec-pp …(truncated)