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 skills/mochow13/keen-code/commitnpx skills add mochow13/keen-code --skill commitgit clone --depth 1 https://github.com/mochow13/keen-codeWhat 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 | $0.00022 | $0.00465 |
| Opus 5 | $0.00011 | $0.00233 |
| Sonnet 5 | $0.00004 | $0.00093 |
| Haiku 4.5 | $0.00002 | $0.00047 |
Grade A, and why
commit 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.
What it actually says
Commit Skill
User intent (optional): $ARGUMENTS
Steps
-
Survey the working tree. Run in parallel:
git status --shortgit diff --stagedgit diffgit log -n 5 --oneline
Use the log to learn the repo's commit-message style (conventional commits, plain sentences, scope prefixes, etc.).
-
Decide what to stage.
- Stage tracked changes the user clearly intends to commit. Name files explicitly with
git add <path>. - If there are untracked files, list them to the user and ask which (if any) should be included. Do not stage them silently.
- Do not use
git add -Aorgit add .— they can leak secrets or stray files.
- Stage tracked changes the user clearly intends to commit. Name files explicitly with
-
Draft the message.
- Lead with why over what. The diff already shows the what.
- Match the recent
git logstyle. - Subject line under ~72 characters. If a body is needed, separate with a blank line.
- If the user provided intent in the line above, weave it in — do not quote it verbatim.
- Do not add co-author or "generated with" trailers unless the user explicitly asks.
-
Commit. Use a heredoc so multi-line bodies survive shell quoting:
git commit -m "$(cat <<'EOF' <subject> <optional body> EOF )" -
Verify. Run
git statusand report the result to the user. Do not push — that is a separate, explicit step the user must request.
On hook failures
If a pre-commit hook fails, do not retry with --no-verify. Read the hook output, fix the underlying issue, re-stage the affected files, and create a new commit. Never amend in this case — the prior commit did not happen, so --amend would target the wrong thing.
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 · 51 lines · 22 tokens per session scan A ede46a503a4e
commit is a skill published in the GitHub repository mochow13/keen-code (60 stars, last pushed 3d ago), licensed MIT. It adds 22 tokens to every session and 465 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 skills, from other repositories
tlamatini-self-update-inclusion
Sweep the whole codebase and keep the SELF-UPDATE pipeline complete — so every new asset/feature added to Tlamatini is actually carried into a release by build.py AND survives (or is correctly replaced by) the self-update swap. Invoke whenever you add/rename a new agent, top-level file or directory, dependency…
tlamatini-self-modify-inclusion
Sweep the whole codebase and keep the SELF-MODIFY source snapshot complete — so the TlamatiniSourceCode/ tree that a --self-modify build ships carries every source/build asset Tlamatini needs to read, modify, and REBUILD herself, with heavy media/secrets correctly omitted+redacted and omitted binaries listed in the…
tlamatini-daily-chat-test
Run the daily automated Tlamatini chat regression — drive a visible Chrome via Playwright, log into agentpage.html, ask up to 1000 curated safe questions one-by-one (Multi-Turn ON, ACPX/Ask-Execs/Exec-Report/Internet OFF), wait for and qualify each answer (heuristic + LLM judge on failures), then write a dated report…
adding-external-mcp
The authoritative reference for adding a NEW external MCP server to Tlamatini universal MCP client layer. Covers the full lifecycle: catalog import, transport selection, activation, runtime provisioning, diagnosis, verification, and troubleshooting. READ THIS BEFORE calling externalmcpimport, before editing…
setup-new-acpx-key
Configure the API key (or other credential) for a registered ACPX agentid (claude/codex/cursor/gemini/qwen/copilot/pi/droid/iflow/kilocode/kimi/kiro/opencode/tlamatini) end-to-end across data.keys, config.json (top-level + acpx.agents. .env), regensecrets.py, and verification via acpdoctor.
tlamatini-agent-naming
The authoritative Tlamatini agent NAMING CONVENTION — invoke before adding, renaming, casing, displaying, or auditing any workflow agent (STM32er, Node Manager, ACPXer, Kalier, ...). Use whenever you touch agentDescription, a pool/agent directory, a CSS .canvas-item class, a JS connection handler…