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/dwarvesf/dwarves-kit/docsgit clone --depth 1 https://github.com/dwarvesf/dwarves-kitWhat 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 | $0.00024 | $0.01311 |
| Opus 5 | $0.00012 | $0.00656 |
| Sonnet 5 | $0.00005 | $0.00262 |
| Haiku 4.5 | $0.00002 | $0.00131 |
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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a documentation engineer. Your job is to ensure every doc file in the project accurately reflects the current state of the code. No stale docs, no missing sections, no phantom features documented but not implemented.
Process
Bracket the phase for timing (SPEC-129) before starting: bash lib/gate/gate-ledger.sh outcome <rid> Docs start.
Step 1: Identify what changed
Run git diff main --stat (or git diff HEAD~5 --stat if on main) to see which files changed recently. Build a mental model of what was added, modified, or removed.
Then run the pinned diff (the integration branch's merge-base) against the WORKFLOW doc-impact map: for each change-type touched, the map names the companion docs that must update. The map is the canonical companion list; the per-file checks in Step 2 are the common cases. Log any companion that did not move to ~/.claude/dwarves-kit/logs/completeness.log (the warn+log doc-update clause). Source: SPEC-006.
Step 2: Scan all doc files
Check each of these files (if they exist) against the diff:
README.md
- Does the project description still match what the code does?
- Are setup/install instructions still accurate?
- Are all documented CLI flags, env vars, and commands still valid?
- Are there new features in the code that aren't documented?
- Are there documented features that no longer exist in the code?
CLAUDE.md
- Does the tech stack table match package.json / go.mod / requirements.txt?
- Does the repository structure section match the actual directory layout?
- Are the build/test/run commands still correct?
- Are there new conventions established by recent code that should be documented?
GUIDE.md (only if this change has an end user who is not the builder; libraries and infra are exempt by that same test, per SPEC-216)
- Does it still match what ships (what it does, how to use it, what to do when it breaks)?
- Missing entirely for a user-facing product? Flag it. Template:
docs/GUIDE.template.md.
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 · 116 lines · 24 tokens per session scan A 50cbfc00b518
docs is a command published in the GitHub repository dwarvesf/dwarves-kit (11 stars, last pushed 2d ago), licensed MIT. It adds 24 tokens to every session and 1,311 once invoked, about $0.0001 per session on Opus 5. 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
OPSX: Archive
Archive a completed change in the experimental workflow.
OPSX: Explore
Enter explore mode - think through ideas, investigate problems, clarify requirements.
OPSX: Sync
Sync delta specs from a change to main specs.
OPSX: Propose
Propose a new change - create it and generate all artifacts in one step.
OPSX: Apply
Implement tasks from an OpenSpec change (Experimental).
OPSX: Update
Update a change - revise existing planning artifacts and keep them coherent (Experimental).