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/redai-infra/relax/git-commitnpx skills add redai-infra/Relax --skill git-commitgit clone --depth 1 https://github.com/redai-infra/RelaxWhat 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 | $0.00073 | $0.01330 |
| Opus 5 | $0.00036 | $0.00665 |
| Sonnet 5 | $0.00015 | $0.00266 |
| Haiku 4.5 | $0.00007 | $0.00133 |
Grade A, and why
git-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.
How it starts
The opening of the file, as written. The whole thing — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Git commit
Creates git commits following Conventional Commits format with rich markdown body.
Recent project commits
!git log --oneline -5 2>/dev/null
Quick start
# 0. Inspect current state
git status -sb
git diff --cached --stat
git diff --stat
# 1. Stage only the intended changes
git add <files>
git diff --cached --stat
# 2. Run pre-commit checks (MUST do before committing)
pre-commit run --all-files --show-diff-on-failure
# If it fails or auto-fixes files: re-stage with git add, then re-run until clean
# 3. Re-stage intended files (pre-commit may have modified files), then verify index
git add <files>
git diff --cached --stat
git diff --stat
# 4. Create commit with detailed markdown body
git commit -F /tmp/commitmsg.txt
Staging discipline
- Treat the index as the source of truth for the commit. Use
git diff --cached --statandgit diff --cached --name-statusbefore writing the message. - Do not infer commit contents from memory,
git diffalone, or previous discussion. Ifgit diff --statis empty butgit status -sbshowsM <file>, the changes are staged. - Leave unrelated untracked files and unrelated unstaged edits alone unless the user explicitly asks to include them.
- Do not use broad
git add .when unrelated untracked files exist. Stage explicit paths. - After pre-commit, re-check both staged and unstaged diffs. If hooks changed files, stage only the intended paths and rerun pre-commit until clean.
- If
git commitfails with.git/index.lock: Operation not permittedin a sandboxed environment, do not restage or modify files. Rerun onlygit commit -F /tmp/commitmsg.txtwith the required sandbox escalation, then remove the temp file after success.
Commit message structure
1. Subject line (first line)
type(scope): concise imperative description
2. Blank line
A mandatory blank line separating the subject from the body.
3. Markdown body (required for all non-trivial commits)
Use first-level headings (#) for each change type, second-level headings (##) for specific changes, bullet points for details, and --- separator between multiple types.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 157 lines · 73 tokens per session scan A 21204e74a78d
git-commit is a skill published in the GitHub repository redai-infra/Relax (580 stars, last pushed 4d ago), licensed Apache-2.0. It adds 73 tokens to every session and 1,330 once invoked, about $0.0004 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
verl-rl-training
Provides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL). Use when implementing RLHF, GRPO, PPO, or other RL algorithms for LLM post-training at scale with flexible infrastructure backends.
openrlhf-training
High-performance RLHF framework with Ray+vLLM acceleration. Use for PPO, GRPO, RLOO, DPO training of large models (7B-70B+). Built on Ray, vLLM, ZeRO-3. 2× faster than DeepSpeedChat with distributed architecture and GPU resource sharing.
openrlhf-training
High-performance RLHF framework with Ray+vLLM acceleration. Use for PPO, GRPO, RLOO, DPO training of large models (7B-70B+). Built on Ray, vLLM, ZeRO-3. 2× faster than DeepSpeedChat with distributed architecture and GPU resource sharing.
verl-rl-training
Provides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL). Use when implementing RLHF, GRPO, PPO, or other RL algorithms for LLM post-training at scale with flexible infrastructure backends.
openrlhf-training
High-performance RLHF framework with Ray+vLLM acceleration. Use for PPO, GRPO, RLOO, DPO training of large models (7B-70B+). Built on Ray, vLLM, ZeRO-3. 2× faster than DeepSpeedChat with distributed architecture and GPU resource sharing.
grpo-rl-training
Expert guidance for GRPO/RL fine-tuning with TRL for reasoning and task-specific model training.