Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add commands/paulonasc/orchestra/docsgit clone --depth 1 https://github.com/paulonasc/orchestraWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00000 | $0.01101 |
| Opus 5 | $0.00000 | $0.00550 |
| Sonnet 5 | $0.00000 | $0.00220 |
| Haiku 4.5 | $0.00000 | $0.00110 |
Grade A, and why
docs scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/o docs — Audit and update documentation
Scans all documentation in the repo (and linked repos) against recent changes. Finds what's stale and offers to fix it.
IMPORTANT: Delegate to a subagent. Doc audits read every doc file + git log + cross-reference — extremely context-heavy. Spawn an Agent with the task, let it do the reads/writes, get back a summary of what's stale and what it fixed. Only bring results back to the main context if the user needs to approve changes.
Flow:
-
Discover docs — find all documentation files in the repo:
README.md,CONTRIBUTING.md,ARCHITECTURE.md,CLAUDE.mdat repo rootdocs/directory if it exists- Any
.mdfiles in key directories that serve as documentation
-
Gather recent changes — read the git log since the last
/o docsrun (or last 7 days if first run):git log --since="7 days ago" --name-only --pretty=format:"%s" -
Cross-reference — for each doc file, check if recent changes affect what it describes:
- Does
README.mdreference files, APIs, commands, or patterns that changed? - Does
ARCHITECTURE.mddescribe a structure that was reorganized? - Does
CLAUDE.mdlist commands or patterns that were added/removed? - Are there new features with zero documentation?
- Does
-
Report and fix — render a summary:
## Doc audit README.md ⚠ stale — mentions old API endpoint /v1/auth, now /v2/auth ARCHITECTURE.md ✓ current CLAUDE.md ⚠ stale — missing new BullMQ task "process-videos" docs/api.md ⚠ stale — 3 new endpoints not documented Fix these now? (y/n)If the user says yes (or doesn't object), update the docs inline. Show the diff for each change.
Key rules:
- Don't rewrite docs from scratch — make targeted updates to stale sections
- Preserve the doc's existing style and voice
- If a doc references code, verify the references are still valid (file paths, function names, CLI commands)
- Track the last audit date in
state/sessions/{session-id}.mdso subsequent runs only check new changes
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 85 lines · 0 tokens per session scan A 5a7851a1cf81
docs is a command published in the GitHub repository paulonasc/orchestra (15 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,101 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.