Pp Cosmos

Cosmos — Printing Press CLI

Prerequisites: Install the CLI

This skill drives the cosmos-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:

   npx -y @mvanhorn/printing-press-library install cosmos --cli-only
   

2. Verify: cosmos-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:

go install github.com/mvanhorn/printing-press-library/library/productivity/cosmos/cmd/cosmos-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.

cosmos-pp-cli mirrors the replayable Cosmos GraphQL surface, then adds confirmed writes, JSON and HTML exports, local membership snapshots, cross-collection analysis, and attribution-aware workflows. Browser automation was used only during development discovery; normal commands use ordinary HTTP and remain scriptable.

When to Use This CLI

Use cosmos-pp-cli when a task involves searching Cosmos, reading or organizing collections, exporting references, preserving attribution, or answering questions across a synced inspiration library. Prefer the compound review, coverage, overlap, provenance, trail, and diff commands when the request spans more than one API operation.

Anti-triggers

Do not use this CLI for:

• Do not use it as a general web image search unrelated to Cosmos.
• Do not use it to generate or semantically classify images.
• Do not use it for destructive bulk writes without explicit user confirmation.

Unique Capabilities

These capabilities aren't available in any other tool for this API.

Local state that compounds

• review — Turn recent saves, unfiled elements, duplicate connections, AI flags, and missing attribution into a deterministic maintenance queue.

  Use it before a weekly curation session to see exactly what needs attention.

  cosmos-pp-cli review --since 7d --json
  

Cross-collection intelligence

• collection overlap — Compare two collections and report shared elements, duplicate media, and references unique to each side.

  Use it to keep project moodboards distinct and avoid recycling the same references.

  cosmos-pp-cli collection overlap 101 202 --json
  

• collection coverage — Compare live Cosmos search results with live collection membership and return promising references that are not already saved.

  Use it when a board feels repetitive and you need genuinely new references.

  cosmos-pp-cli collection coverage --collection 101 --query 'brutalist typography' --limit 20 --json
  

Trustworthy creative archives

• provenance audit — Report missing source URLs or authors and show source concentration from live collection elements.

  Use it before publishing or handing off a moodboard so references remain attributable.

  cosmos-pp-cli provenance audit --collection 101 --json
  

• snapshot diff — Compare historical collection membership and show added, removed, and moved elements.

  Use it to audit a team's curation changes or reproduce an earlier moodboard state.

  cosmos-pp-cli snapshot diff --from 7d --to now --json
  

Discovery that compounds

• element trail — Walk visual similarity results to a bounded depth and emit a deduplicated, source-aware graph.

  Use it to explore a visual direction without losing the path back to the seed reference.

  cosmos-pp-cli element trail --id 2113061259 --depth 2 --limit 12 --json
  

Discovery Signals

This CLI was generated from a sanitized authenticated, read-only browser capture.

• 37 distinct Cosmos GraphQL operations were retained.
• Standard HTTP to https://api.cosmos.so/graphql is sufficient; do not launch a browser for normal CLI work.
• Select a tenant-gated client profile whose credential reference is env:COSMOS_TOKEN; never echo credentials into logs.
• Writes require --yes (or --agent) and support --dry-run before validation.

Command Reference

The public surface is curated; captured GraphQL operation families are internal implementation details and are not executable commands. Use --help on these stable command groups:

• discover - search elements and collections or browse featured references
• collection - list, inspect, create, connect, compare, and audit collections
• element - inspect, save, connect, and explore visual references
• activity list and feed - inspect account activity and the personalized feed
• review and provenance audit - find filing, duplication, and attribution issues
• sync and snapshot diff - capture profile-scoped membership history and compare it
• export collection and export gallery - write explicit user-selected output files
• import status - inspect active Cosmos imports without accepting caller-supplied GraphQL
• identity, whoami, and doctor - verify the selected tenant-gated account

Recipes

Export an attributed project collection

cosmos-pp-cli export collection 101 --output ./collection-101.json --json

Exports normalized element, media, and source-attribution metadata as JSON.

Find gaps in a moodboard

cosmos-pp-cli collection coverage --collection 101 --query 'warm modernist interiors' --limit 30 --json

Returns live search candidates not already connected to the collection.

Audit attribution before handoff

cosmos-pp-cli provenance audit --collection 101 --json

Shows missing sources and concentration by source domain without crawling third-party sites.

Auth Setup

Public discovery commands work without a token. Personal collections and writes use a Cosmos bearer token supplied through COSMOS_TOKEN. Run cosmos-pp-cli auth identify --json, then create a tenant-gated client profile whose credential reference is env:COSMOS_TOKEN; credentials are never included in exported manifests or JSON output.

Run cosmos-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:

  cosmos-pp-cli collection list --agent --select id,name
  

• Previewable — --dry-run shows the request without sending

• Non-interactive — never prompts, every input is a flag

• Explicit retries — use --idempotent only when an already-existing create should count as success

Paths and state

Agents should treat the CLI's path resolver as part of the runtime contract:

• Use --home <dir> for one invocation, or set COSMOS_HOME=<dir> to relocate all four path kinds under one root.

• Use per-kind env vars only when a specific kind must diverge: COSMOS_CONFIG_DIR, COSMOS_DATA_DIR, COSMOS_STATE_DIR, COSMOS_CACHE_DIR.

• Resolution order is per-kind env var, --home, COSMOS_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 data.db and private, client-profile-scoped cosmos-snapshots/*.json files. state contains persisted queries, jobs, and teach.log. cache contains regenerable HTTP/cache files.

• Cosmos tokens remain in COSMOS_TOKEN; this CLI does not persist them to its config or data directories.

• Run cosmos-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:

  {
    "mcpServers": {
      "cosmos": {
        "command": "cosmos-pp-mcp",
        "env": {
          "COSMOS_HOME": "/srv/cosmos"
        }
      }
    }
  }
  

Fleet precedence: an inherited per-kind env var overrides an explicit --home for that kind. Use COSMOS_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 COSMOS_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:

cosmos-pp-cli recall "<user's question>" --agent

The response envelope:

{
  "query": "...",
  "normalized": "<normalized form>",
  "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": ["<trial command>", "cosmos-pp-cli learnings confirm 12"] }
  ],
  "playbook": {
    "query_family": "...",
    "playbook": {
      "steps": [ { "cmd": "<command with {slot} substitution>", "purpose": "..." } ],
      "entity_slots": ["$ENTITY"],
      "expected_tool_calls": 3
    },
    "slots_resolved": { "$ENTITY": { "token": "<live token>", "canonical": "<canonical>" } },
    "notes": "<workarounds + gotchas for this query family>"
  },
  "notes": "<duplicate surface for non-playbook callers>"
}

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 <id>` only after the trial verified the behavior.
       Reject a wrong candidate with `learnings reject <id>`.
    -> 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 `cosmos-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 <id> prints the candidate's full payload before materializing it - check that the printed payload matches the behavior you verified. learnings reject <id> tombstones the derivation signature so the same candidate does not resurface. The envelope carries only the few candidates worth acting on now; cosmos-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:<canonical> (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.
• 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:

cosmos-pp-cli teach --query "<user's question>" --resource-type <type> --resource <id1> --resource <id2>
# (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:

# Common case: record both the resource learning AND the playbook in one call.
cosmos-pp-cli teach \
  --query "<user's question>" \
  --resource <id> \
  --playbook-file ~/playbooks/<shape>.json \
  --playbook-notes-file ~/playbooks/<shape>-notes.md
# (append shell `&` to background it)

# Alternate: playbook-only (no resource to record alongside).
cosmos-pp-cli teach-playbook \
  --query "<user's question>" \
  --playbook-file ~/playbooks/<shape>.json \
  --notes-file ~/playbooks/<shape>-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.

cosmos-pp-cli playbook amend \
  --query "<exact recall query string>" \
  --add-note "<your concrete correction>"
# (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]: <text>). 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

cosmos-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.
• COSMOS_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:

cosmos-pp-cli feedback "the --since flag is inclusive but docs say exclusive"
cosmos-pp-cli feedback --stdin < notes.txt
cosmos-pp-cli feedback list --json --limit 10

Entries are stored locally as feedback.jsonl under the resolved data dir. They are never POSTed unless COSMOS_FEEDBACK_ENDPOINT is set AND either --send is passed or COSMOS_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 <sink>. 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:

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.

cosmos-pp-cli profile save briefing --json
cosmos-pp-cli --profile briefing activities --operation-name example-resource
cosmos-pp-cli profile list --json
cosmos-pp-cli profile show briefing
cosmos-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

Argument Parsing

Parse $ARGUMENTS:

1. Empty, help, or --help → show cosmos-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

1. Install the MCP server:

   go install github.com/mvanhorn/printing-press-library/library/productivity/cosmos/cmd/cosmos-pp-mcp@latest
   

2. Register with Claude Code:

   claude mcp add cosmos-pp-mcp -- cosmos-pp-mcp
   

3. Verify: claude mcp list

Direct Use

1. Check if installed: which cosmos-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:

   cosmos-pp-cli <command> [subcommand] [args] --agent
   

4. If ambiguous, drill into subcommand help: cosmos-pp-cli <command> --help.