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/niclejeune/pi-agents-config/commitnpx skills add niclejeune/pi-agents-config --skill commitgit clone --depth 1 https://github.com/niclejeune/pi-agents-configWhat 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 | $0.00009 | $0.00494 |
| Opus 5 | $0.00005 | $0.00247 |
| Sonnet 5 | $0.00002 | $0.00099 |
| Haiku 4.5 | $0.00001 | $0.00049 |
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.
This is a copy
100% identical to commit — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create a git commit for the current changes using Conventional Commits format with a polished, highly descriptive message. If there are commit hooks - do not skip them, it's your responsability to leave things better than they were.
Format
<type>(<scope>): <summary>
typeREQUIRED. Usefeatfor new features,fixfor bug fixes. Other common types:docs,refactor,chore,test,perf.scopeOPTIONAL. Short noun in parentheses for the affected area (e.g.,api,parser,ui).summaryREQUIRED. Short, imperative, <= 72 chars, no trailing period.
Notes
- Body is strongly encouraged — always include one unless the change is trivially obvious (e.g., fixing a typo). The body should explain what changed, why it changed, the approach taken, and any notable decisions. A reader of
git logshould understand the change without looking at the diff. - Do NOT include breaking-change markers or footers.
- Do NOT add sign-offs (no
Signed-off-by). - Only commit; do NOT push.
- If it is unclear whether a file should be included, ask the user which files to commit.
- Treat any caller-provided arguments as additional commit guidance. Common patterns:
- Freeform instructions should influence scope, summary, and body.
- File paths or globs should limit which files to commit. If files are specified, only stage/commit those unless the user explicitly asks otherwise.
- If arguments combine files and instructions, honor both.
Steps
- Infer from the prompt if the user provided specific file paths/globs and/or additional instructions.
- Review
git statusandgit diffto understand the current changes (limit to argument-specified files if provided). - (Optional) Run
git log -n 50 --pretty=format:%sto see commonly used scopes. - If there are ambiguous extra files, ask the user for clarification before committing.
- Stage only the intended files (all changes if no files specified).
- Run
git commit -m "<subject>"(and-m "<body>"if needed).
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 · 37 lines · 9 tokens per session scan A 3edb133ecf9b
commit is a skill published in the GitHub repository niclejeune/pi-agents-config (2 stars, last pushed 4mo ago), licensed MIT. It adds 9 tokens to every session and 494 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to commit, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
brpr
(devtools plugin) Create a branch, commit changes, push, and open a PR — or just commit+push+PR if already on a feature branch. Links related issues from GitHub or Linear based on project tracker config.
flow-next-work
Execute a flow-next spec or task end-to-end with worker subagents, gates, and commits. Use when asked to work on, implement, or execute fn-N.
setup-caliber
Sets up Caliber for automatic AI agent context sync. Installs pre-commit hooks so CLAUDE.md, Cursor rules, and Copilot instructions update automatically on every commit. Use when Caliber hooks are not yet installed or when the user asks about keeping agent configs in sync.
trellis-finish-work
Wrap up the current session: verify quality gate passed, remind user to commit, archive completed tasks, and record session progress to the developer journal. Use when done coding and ready to end the session.
kn-commit
Use when committing code changes with proper conventional commit format and verification.
campaign-commit
Choose the correct commit command in a campaign workspace. Use when you are about to commit and need to select camp commit, camp p commit, fest commit, or intentional root pointer sync via camp refs-sync.