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 skills add kreek/consult --skill commitgit clone --depth 1 https://github.com/kreek/consultWrote 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/skills/kreek/consult/commit)<a href="https://agentmods.dev/skills/kreek/consult/commit"><img src="https://agentmods.dev/badge/skills/kreek/consult/commit/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/skills/kreek/consult/commit"><img src="https://agentmods.dev/badge/skills/kreek/consult/commit.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 | $0.00016 | $0.00669 |
| Opus 5.5 | $0.00006 | $0.00268 |
| Sonnet 5.5 | $0.00003 | $0.00134 |
| Haiku 4.5 | $0.00002 | $0.00067 |
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 14d 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Commit
Iron Law
COMMIT ONLY THE REVIEWED SLICE. STAGE FILES BY NAME.
The host owns git invocation; this skill sets the packaging standard.
When to Use
- The user asks to commit, stage, split, or package current changes.
- Dirty files need grouping into logical commits, or a commit needs a subject and body.
When NOT to Use
- Branches, conflicts, rebases, recovery, force-push, GitHub; use
git-workflow. - Reviewing the diff; use
code-reviewfirst for non-trivial work. - Versions, changelogs, tags, publishing; use
releasewhen approved.
Rules
- Check the tree state first and stop on anything unexpected: wrong branch, unresolved merge state, files you do not recognize.
- A branch is not the commit boundary. Group changes by behavior so one behavior can be reverted without dragging unrelated work. Nearby work that would need a different rollback decision waits for its own commit.
- Stage only named files or approved pathspecs for the reviewed slice. Never
git add .in a messy tree. Confirm the staged diff matches the slice. Unrelated dirty or untracked files stay unstaged and are named as deferred. - Confirm the relevant proof is current before committing. If a broad suite is noisy for unrelated reasons, name the targeted proof and report the drift separately.
- The subject completes "When applied, this commit will ...". Add a body only when the change needs context, at most 2-3 short paragraphs.
- Attribution trailers are host configuration, not message content. When a
host adds
Co-Authored-Byor similar by default, point the user at the setting that disables it (includeCoAuthoredBy: falsein Claude Code) rather than overriding the host from inside the message. - Never skip hooks. Run the hook, or fix and report its blocker.
Tripwires
| Trigger | Do this instead | False alarm |
|---|---|---|
| "git add . is faster" | Stage named files or approved pathspecs only. | Fresh scaffold with a clean tree where every file belongs. |
| "Commit everything dirty" | Separate reviewed work from unrelated files first. | The user explicitly approved the full dirty tree. |
| "Skip hooks to save time" | Run the hook or fix and report its blocker. | None. |
| "Add Co-Authored-By or AI attribution" | Suggest the host setting that disables generated trailers, such as includeCoAuthoredBy: false in Claude Code. |
The user explicitly requested a specific trailer. |
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.
- 14d ago Changed · +3 tokens per session 69a2c51fca46
- 1mo ago Changed · -27 lines 59daf5961f0d
- 1mo ago First seen · 91 lines · 13 tokens per session scan A 7c0c8f125d39
commit is a skill published in the GitHub repository kreek/consult (1 stars, last pushed 14d ago), licensed MIT. It adds 16 tokens to every session and 669 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 2026-08-31.
Other skills, from other repositories
pr-review
Address feedback left on a GitHub pull request: fetch unresolved review threads, make agreed Elixir/Phoenix code fixes, reply, and resolve. Use for a PR URL/number or reviewer comments. NOT for pre-PR review, findings triage, or CI monitoring.
phx-pr-review
Address feedback left on a GitHub pull request: fetch unresolved review threads, make agreed Elixir/Phoenix code fixes, reply, and resolve. Use for a PR URL/number or reviewer comments. NOT for pre-PR review, findings triage, or CI monitoring.
genshijin-commit
A guide for writing short Git commit messages in Conventional Commits format, a shared style that labels changes such as features, fixes, tests, and documentation. It supports Japanese and English and emphasizes explaining why a change was made.
branch-and-worktree-workflow
Isolates feature work in its own branch or worktree and integrates it cleanly when done. Use this when starting work that should not disturb the current workspace, when several efforts must proceed in parallel on one repository, or when implementation is finished and the change needs merging, rebasing, or splitting…
post-commit
Use when a code commit just landed (not wip/amend/undo) and CHANGELOG or plugin-version post-commit actions are needed.
commit-detection
Detects optimal commit type from git changes. Use when analyzing commits, determining commit type, or before committing.