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/e1024kb/wise-claude/wise-commitnpx skills add e1024kb/wise-claude --skill wise-commitgit clone --depth 1 https://github.com/e1024kb/wise-claudeWhat 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 | $0.00180 | $0.01260 |
| Opus 5 | $0.00090 | $0.00630 |
| Sonnet 5 | $0.00036 | $0.00252 |
| Haiku 4.5 | $0.00018 | $0.00126 |
Grade A, and why
wise-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 yesterday.
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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/wise-commit — draft a Conventional-Commits subject and commit
Why this skill exists
/wise-commit-message is read-only on purpose: it drafts a subject
and hands it back, so the user can review, tweak, or reject the
prose before any commit object exists. That's the right shape when
the operator is sitting at the keyboard.
/wise-commit is the right shape when the operator already trusts
the drafter to pick the type, scope, and prose — they want one
call that stages tracked modifications, drafts the subject, and
commits. No clipboard round-trip, no second invocation.
The skill is a thin wrapper: read the shared
commit-routine.md, set PUSH=no
and SIMPLIFY=yes, and follow it. The routine is the source
of truth for staging discipline, the §2 pre-staging simplify
pass, Jira detection, type classification, and the final-line
emit format. Pushing is /wise-commit-push's job; the per-caller
SIMPLIFY default policy lives in the routine's §"Inputs the
caller sets".
Invocation
/wise-commit
/wise:wise-commit # canonical namespaced form
No positionals, no flags. If the argument string contains anything other than optional whitespace, stop with:
Unknown argument(s): <the extra tokens>
Usage: /wise-commit
If the user wants --no-verify, partial staging, or --amend, they
run git commit directly. This skill's argument surface is
deliberately empty so the routine's behaviour is predictable.
Procedure
1. Read the shared routine
Read ${CLAUDE_PLUGIN_ROOT}/skills/wise-commit/commit-routine.md (the
file that ships alongside this SKILL.md).
2. Run the routine with PUSH=no and SIMPLIFY=yes
Set PUSH=no and SIMPLIFY=yes, then follow the routine
end-to-end. PUSH=no skips §8 (push) entirely; SIMPLIFY=yes runs
the §2 simplify pass before staging so its edits land in the same
commit (a simplify error stops the routine with
COMMIT: failed reason="simplify errored: …" and nothing staged).
The routine owns everything else — staging discipline, Jira scope,
classification, subject drafting, the commit, and the final-line emit.
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.
- yesterday First seen · 137 lines · 180 tokens per session scan A cc20f2f12948
wise-commit is a skill published in the GitHub repository e1024kb/wise-claude (4 stars, last pushed 6d ago), licensed MIT. It adds 180 tokens to every session and 1,260 once invoked, about $0.0009 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…