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.
git clone --depth 1 https://github.com/fusengine/agentsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/fusengine/agents/docs)<a href="https://agentmods.dev/commands/fusengine/agents/docs"><img src="https://agentmods.dev/badge/commands/fusengine/agents/docs/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/fusengine/agents/docs"><img src="https://agentmods.dev/badge/commands/fusengine/agents/docs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00018 | $0.00344 |
| Opus 5.5 | $0.00007 | $0.00138 |
| Sonnet 5.5 | $0.00004 | $0.00069 |
| Haiku 4.5 | $0.00002 | $0.00034 |
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 7d 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.
What it actually says
Documentation Commit
Current State
!git status
Documentation Files Changed
!git diff --stat -- '*.md' '*.txt' '*.rst'
Instructions
Create a documentation commit.
- Stage only documentation files:
*.mdfiles*.txt,*.rstfiles- Files with only comment/JSDoc changes
- Analyze files to determine scope
- Generate commit message:
- If
$ARGUMENTSprovided:docs(scope): $ARGUMENTS - If empty: generate from file names
- If
- Format:
docs(scope): imperative description - NO AI SIGNATURE: Never add Co-authored-by, Generated by, or any AI mention
- Ask confirmation before committing
- Execute and show result
- Execute the
post-commitskill (CHANGELOG + version bump only — no tag here; tagging is handled post-merge by/fuse-commit-pro:commit's Steps 7–9 (merge, tag, release-workflow watch), not by this quick command — never call a release "published" from here)
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.
- 7d ago Changed a0d223eb4f1c
- 1mo ago First seen · 35 lines · 18 tokens per session scan A 3f33ac15e659
docs is a command published in the GitHub repository fusengine/agents (33 stars, last pushed 7d ago), licensed MIT. It adds 18 tokens to every session and 344 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-03.
Other commands, from other repositories
genshijin-commit
A command that writes a commit message for changes already placed in Git's staging area. It follows the repository's existing language and uses a short imperative subject without AI attribution.
commit-claude-config
Un-ignore and commit the kit config (.claude/, CLAUDE.md, .mcp.json, .gitmodules).
quick-commit
Format, lint and commit with a conventional message on a kit-named branch.
nyann:commit
Generate a Conventional Commits message from the staged diff and commit after confirmation. Same flow as the natural-language commit skill — dispatches here so users who prefer explicit slash commands can bypass intent detection.
migrate-ledger
(Ledger) Move a pre-2.0 in-repo Agile-Ledger/ folder into the ledger repo, then clean the code repo.
init-ledger
(Ledger) Create the ledger repository — Registry + Config — the one-time setup.