# Pp Paperclip > Printing Press CLI for Paperclip. REST API for the Paperclip AI agent management platform - Skill: `mvanhorn-printing-press-libra/pp-paperclip` (Agent Skill) - Install (CLI): `npx skillmds add mvanhorn-printing-press-libra/pp-paperclip` - Raw SKILL.md: https://api.skillmd.com/api/skills/mvanhorn-printing-press-libra/pp-paperclip/raw - Safety review: pending - Works with: Claude Code, Claude.ai, OpenAI Codex - Category: AI & ML - 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-paperclip --- # Paperclip — Printing Press CLI ## Prerequisites: Install the CLI This skill drives the `paperclip-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 `$HOME/.local/bin` on macOS/Linux and `%LOCALAPPDATA%\Programs\PrintingPress\bin` on Windows: ```bash npx -y @mvanhorn/printing-press-library install paperclip --cli-only ``` 2. Verify: `paperclip-pp-cli --version` 3. Ensure the reported install directory is on `$PATH` for the agent/runtime that will invoke this skill. If the `npx` install fails before this CLI has a public-library category, install Node or use the category-specific Go fallback after publish. 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. REST API for the Paperclip AI agent management platform ## Command Reference **adapters** — Manage adapters - `paperclip-pp-cli adapters create` — Install an adapter - `paperclip-pp-cli adapters delete` — Delete an adapter - `paperclip-pp-cli adapters get` — Get adapter registration details - `paperclip-pp-cli adapters list` — List all adapters - `paperclip-pp-cli adapters update` — Enable or disable an adapter **admin** — Manage admin - `paperclip-pp-cli admin create` — Demote a user from instance admin - `paperclip-pp-cli admin create-users` — Promote a user to instance admin - `paperclip-pp-cli admin get` — Get company access for a user (admin) - `paperclip-pp-cli admin list` — List all users (admin) - `paperclip-pp-cli admin update` — Set company access for a user (admin) **agents** — Manage agents - `paperclip-pp-cli agents delete` — Delete an agent - `paperclip-pp-cli agents get` — Get an agent - `paperclip-pp-cli agents list` — Get the current agent - `paperclip-pp-cli agents list-me` — Get current agent inbox (lite) - `paperclip-pp-cli agents list-me-2` — Get current agent assigned inbox items - `paperclip-pp-cli agents update` — Update an agent **approvals** — Manage approvals - `paperclip-pp-cli approvals ` — Get an approval **assets** — Manage assets **attachments** — Manage attachments - `paperclip-pp-cli attachments ` — Delete an attachment **auth** — Manage auth - `paperclip-pp-cli auth list` — Get current session - `paperclip-pp-cli auth list-profile` — Get current user profile - `paperclip-pp-cli auth update` — Update current user profile **board** — Manage board - `paperclip-pp-cli board` — Stream a board-level chat response (requires enableConferenceRoomChat) **board-api-keys** — Manage board api keys - `paperclip-pp-cli board-api-keys create` — Create a named board API key - `paperclip-pp-cli board-api-keys delete` — Revoke a board API key - `paperclip-pp-cli board-api-keys list` — List board API keys **board-claim** — Manage board claim - `paperclip-pp-cli board-claim ` — Get board claim details by token **bootstrap** — Manage bootstrap - `paperclip-pp-cli bootstrap` — Claim first instance admin from a browser session **cli-auth** — Manage cli auth - `paperclip-pp-cli cli-auth create` — Create a CLI auth challenge - `paperclip-pp-cli cli-auth create-cliauth` — Revoke current CLI auth session - `paperclip-pp-cli cli-auth create-cliauth-2` — Approve a CLI auth challenge - `paperclip-pp-cli cli-auth create-cliauth-3` — Cancel a CLI auth challenge - `paperclip-pp-cli cli-auth get` — Get a CLI auth challenge - `paperclip-pp-cli cli-auth list` — Get current CLI auth session **cloud-upstreams** — Manage cloud upstreams - `paperclip-pp-cli cloud-upstreams create` — Finish a cloud upstream connection - `paperclip-pp-cli cloud-upstreams create-cloudupstreams` — Start a cloud upstream connection - `paperclip-pp-cli cloud-upstreams list` — List cloud upstream connections **companies** — Manage companies - `paperclip-pp-cli companies create` — Create a company - `paperclip-pp-cli companies create-import` — Apply a company import (legacy route) - `paperclip-pp-cli companies create-import-2` — Preview a company import (legacy route) - `paperclip-pp-cli companies delete` — Delete a company - `paperclip-pp-cli companies get` — Get a company - `paperclip-pp-cli companies get-import` — Get company import job status - `paperclip-pp-cli companies list` — List companies - `paperclip-pp-cli companies list-issues` — Legacy — returns error directing to correct issues path - `paperclip-pp-cli companies list-stats` — Company stats - `paperclip-pp-cli companies update` — Update a company **environment-custom-image-setup-sessions** — Manage environment custom image setup sessions - `paperclip-pp-cli environment-custom-image-setup-sessions ` — Get and refresh an environment customImage setup session **environment-leases** — Manage environment leases - `paperclip-pp-cli environment-leases ` — Get an environment lease **environments** — Manage environments - `paperclip-pp-cli environments delete` — Delete an environment - `paperclip-pp-cli environments get` — Get an environment - `paperclip-pp-cli environments update` — Update an environment **execution-workspaces** — Manage execution workspaces - `paperclip-pp-cli execution-workspaces get` — Get an execution workspace - `paperclip-pp-cli execution-workspaces update` — Update an execution workspace **feedback-traces** — Manage feedback traces - `paperclip-pp-cli feedback-traces ` — Get a feedback trace **goals** — Manage goals - `paperclip-pp-cli goals delete` — Delete a goal - `paperclip-pp-cli goals get` — Get a goal - `paperclip-pp-cli goals update` — Update a goal **health** — Manage health - `paperclip-pp-cli health create` — Request a managed dev-server restart - `paperclip-pp-cli health list` — Health check **heartbeat-runs** — Manage heartbeat runs - `paperclip-pp-cli heartbeat-runs ` — Get a heartbeat run **instance** — Manage instance - `paperclip-pp-cli instance create` — Trigger a database backup - `paperclip-pp-cli instance create-settings` — Preview issue graph liveness auto-recovery - `paperclip-pp-cli instance create-settings-2` — Run issue graph liveness auto-recovery - `paperclip-pp-cli instance list` — List scheduler heartbeats - `paperclip-pp-cli instance list-settings` — Get instance settings - `paperclip-pp-cli instance list-settings-2` — Get experimental instance settings - `paperclip-pp-cli instance list-settings-3` — Get general instance settings - `paperclip-pp-cli instance update` — Update instance settings - `paperclip-pp-cli instance update-settings` — Update experimental instance settings - `paperclip-pp-cli instance update-settings-2` — Update general instance settings **invites** — Manage invites - `paperclip-pp-cli invites ` — Get an invite by token **issues** — Manage issues - `paperclip-pp-cli issues delete` — Delete an issue - `paperclip-pp-cli issues get` — Get an issue - `paperclip-pp-cli issues list` — Legacy — returns error directing to /api/companies/{companyId}/issues - `paperclip-pp-cli issues update` — Update an issue **join-requests** — Manage join requests **labels** — Manage labels - `paperclip-pp-cli labels ` — Delete a label **llms** — Manage llms - `paperclip-pp-cli llms get` — Get agent configuration for a specific adapter type - `paperclip-pp-cli llms list` — Get agent configuration as plain text (for LLM context) - `paperclip-pp-cli llms list-agenticonstxt` — Get agent icon names as plain text **openapi-json** — Manage openapi json - `paperclip-pp-cli openapi-json` — Get the generated OpenAPI document **plugins** — Manage plugins - `paperclip-pp-cli plugins create` — Install a plugin - `paperclip-pp-cli plugins create-tools` — Execute a plugin tool - `paperclip-pp-cli plugins delete` — Delete a plugin - `paperclip-pp-cli plugins get` — Get a plugin - `paperclip-pp-cli plugins list` — List installed plugins - `paperclip-pp-cli plugins list-examples` — List example plugins - `paperclip-pp-cli plugins list-tools` — List plugin tools - `paperclip-pp-cli plugins list-uicontributions` — List plugin UI contributions **projects** — Manage projects - `paperclip-pp-cli projects delete` — Delete a project - `paperclip-pp-cli projects get` — Get a project - `paperclip-pp-cli projects update` — Update a project **routine-triggers** — Manage routine triggers - `paperclip-pp-cli routine-triggers create` — Fire a public routine trigger - `paperclip-pp-cli routine-triggers delete` — Delete a routine trigger - `paperclip-pp-cli routine-triggers update` — Update a routine trigger **routines** — Manage routines - `paperclip-pp-cli routines get` — Get a routine - `paperclip-pp-cli routines update` — Update a routine **secret-provider-configs** — Manage secret provider configs - `paperclip-pp-cli secret-provider-configs delete` — Delete a secret provider configuration - `paperclip-pp-cli secret-provider-configs get` — Get a secret provider configuration - `paperclip-pp-cli secret-provider-configs update` — Update a secret provider configuration **secrets** — Manage secrets - `paperclip-pp-cli secrets delete` — Delete a secret - `paperclip-pp-cli secrets update` — Update a secret **sidebar-preferences** — Manage sidebar preferences - `paperclip-pp-cli sidebar-preferences list` — Get current user sidebar preferences - `paperclip-pp-cli sidebar-preferences update` — Update current user sidebar preferences **skills** — Manage skills - `paperclip-pp-cli skills get` — Get a skill by name - `paperclip-pp-cli skills get-catalog` — Get a catalog skill - `paperclip-pp-cli skills get-catalog-2` — List catalog skill files - `paperclip-pp-cli skills list` — List available skills - `paperclip-pp-cli skills list-catalog` — List catalog skills - `paperclip-pp-cli skills list-index` — Get skills index **teams** — Manage teams - `paperclip-pp-cli teams get` — Get catalog team - `paperclip-pp-cli teams get-catalog` — Get catalog team file - `paperclip-pp-cli teams list` — List catalog teams **work-products** — Manage work products - `paperclip-pp-cli work-products delete` — Delete a work product - `paperclip-pp-cli work-products update` — Update a work product **workspace-operations** — Manage workspace operations ### Finding the right command When you know what you want to do but not which command does it, ask the CLI directly: ```bash paperclip-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 Configure one of Paperclip's supported authentication modes: - `PAPERCLIP_SESSION_COOKIE` for a browser session (`board-session`) - `PAPERCLIP_API_KEY` for a board API key (`board-api-key`) - `PAPERCLIP_AGENT_TOKEN` for an agent bearer token (`agent-bearer`) The CLI auto-detects the mode from the credential. Set `PAPERCLIP_AUTH_MODE` to `board-session`, `board-api-key`, `agent-bearer`, or `none` to choose explicitly. Run `paperclip-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 paperclip-pp-cli adapters list --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 - **Explicit retries** — use `--idempotent` only when an already-existing create should count as success, and use `--ignore-missing` only when a missing delete target should count as success ### 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 `PAPERCLIP_HOME=` to relocate all four path kinds under one root. - Use per-kind env vars only when a specific kind must diverge: `PAPERCLIP_CONFIG_DIR`, `PAPERCLIP_DATA_DIR`, `PAPERCLIP_STATE_DIR`, `PAPERCLIP_CACHE_DIR`. - Resolution order is per-kind env var, `--home`, `PAPERCLIP_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 `paperclip-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": { "paperclip": { "command": "paperclip-pp-mcp", "env": { "PAPERCLIP_HOME": "/srv/paperclip" } } } } ``` Fleet precedence: an inherited per-kind env var overrides an explicit `--home` for that kind. Use `PAPERCLIP_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 `PAPERCLIP_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 paperclip-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": ["", "paperclip-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 `paperclip-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; `paperclip-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 `paperclip-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 paperclip-pp-cli teach --query "" --resource-type --resource --resource # (append shell `&` to background it) ``` 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. paperclip-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). paperclip-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 paperclip-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 `paperclip-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. - `PAPERCLIP_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: ``` paperclip-pp-cli feedback "the --since flag is inclusive but docs say exclusive" paperclip-pp-cli feedback --stdin < notes.txt paperclip-pp-cli feedback list --json --limit 10 ``` Entries are stored locally as `feedback.jsonl` under the resolved data dir. They are never POSTed unless `PAPERCLIP_FEEDBACK_ENDPOINT` is set AND either `--send` is passed or `PAPERCLIP_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. ``` paperclip-pp-cli profile save briefing --json paperclip-pp-cli --profile briefing adapters list paperclip-pp-cli profile list --json paperclip-pp-cli profile show briefing paperclip-pp-cli profile delete briefing --yes ``` Explicit flags always win over profile values; profile values win over defaults. `agent-context` lists all available profiles under `available_profiles` so introspecting agents discover them at runtime. ## Exit Codes | Code | Meaning | |------|---------| | 0 | Success | | 2 | Usage error (wrong arguments) | | 3 | Resource not found | | 5 | API error (upstream issue) | | 7 | Rate limited (wait and retry) | | 10 | Config error | ## Argument Parsing Parse `$ARGUMENTS`: 1. **Empty, `help`, or `--help`** → show `paperclip-pp-cli --help` output 2. **Starts with `install`** → ends with `mcp` → MCP installation; otherwise → see Prerequisites above 3. **Anything else** → Direct Use (execute as CLI command with `--agent`) ## MCP Server Installation Install the MCP binary from this CLI's published public-library entry or pre-built release, then register it: ```bash claude mcp add paperclip-pp-mcp -- paperclip-pp-mcp ``` Verify: `claude mcp list` ## Direct Use 1. Check if installed: `which paperclip-pp-cli` If not found, offer to install (see Prerequisites at the top of this skill). 2. Match the user query to the best command from the Unique Capabilities and Command Reference above. 3. Execute with the `--agent` flag: ```bash paperclip-pp-cli [subcommand] [args] --agent ``` 4. If ambiguous, drill into subcommand help: `paperclip-pp-cli --help`.