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 sungurerdim/dev-skills --skill ds-commitgit clone --depth 1 https://github.com/sungurerdim/dev-skillsWrote 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/sungurerdim/dev-skills/ds-commit)<a href="https://agentmods.dev/skills/sungurerdim/dev-skills/ds-commit"><img src="https://agentmods.dev/badge/skills/sungurerdim/dev-skills/ds-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/sungurerdim/dev-skills/ds-commit"><img src="https://agentmods.dev/badge/skills/sungurerdim/dev-skills/ds-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 | $0.00036 | $0.04626 |
| Opus 5.5 | $0.00014 | $0.01850 |
| Sonnet 5.5 | $0.00007 | $0.00925 |
| Haiku 4.5 | $0.00004 | $0.00463 |
Grade A, and why
ds-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 1mo 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 — 244 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/ds-commit
AI commits are vague ("update code"), bundle unrelated changes, and skip pre-commit checks. Skill reads diff, groups changes logically, and writes precise conventional commit messages.
Smart Commits — Quality gates + atomic grouping + conventional commit format.
Completion Evidence — applies to every phase: Report
done/OKonly with the machine-checkable evidence the gates name — the exact command run and its observed output (orfile:linediff). Missing evidence → reportINCOMPLETEplus what is missing. Self-assessment is never evidence. (This band repeats at file end by design — both copies are normative.)
Triggers
- User runs
/ds-commit - User asks to commit, stage and commit, save work as a commit
- Trigger only on explicit commit request — staging alone is not a commit request
Triggers — INVOKE / DON'T INVOKE
| INVOKE | DON'T INVOKE |
|---|---|
| "commit my changes", "save my work as a commit" | "create a pull request" (→ ds-pr) |
| "split this into atomic conventional commits" | "format my code" (→ ds-fix) |
| "stage and commit per logical change" | "tidy commit history of a branch" (→ ds-pr --tidy) |
| "commit + push" (commit only — push is separate) | "merge into main" (→ ds-pr) |
Contract
Dimensions: none (carrier)
Commit message describes only what git diff shows. Not session discussion, not what was tried and reverted, not what was planned. Read diff, describe diff.
- Standalone. Uses blueprint profile for toolchain when available; own detection when absent.
- Full accounting enforced: every finding and planned check ends in an explicit disposition (fixed / skipped + reason / only you can do); summary totals balance.
- Pre-existing / out-of-scope errors detected during work are NOT skipped — fixed inline or escalated with concrete blocker.
- Exempt from state protocol: atomic, git-diff-driven, seconds-long. Git staging area is the natural state. No
ds/audit/commit.json. - A commit never touches the remote. No fetch, no pull, no push — this skill's write surface stops at the local repository.
What ships with it
2 files 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.
- 1mo ago Changed · -6 lines d9b728a4c0e3
- 1mo ago First seen · 250 lines · 36 tokens per session scan A a0b34f200d35
ds-commit is a skill published in the GitHub repository sungurerdim/dev-skills (1 stars, last pushed 1mo ago), licensed MIT. It adds 36 tokens to every session and 4,626 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
ring:generating-pr-descriptions
Generating pull request descriptions from git branch changes with automatic title generation, change-type detection, and smart analysis. Uses branch-only scope to avoid full history analysis. Use when preparing a PR for review. Skip when the PR is a single trivial commit or description already exists.
review
Structured code review with parallel audit agents, confidence-scored triage, and optional auto-fix. Examines uncommitted changes, staged diffs, commit ranges, or specific paths. Produces a tiered report (MUST-FIX / RECOMMENDED / NIT) backed by evidence, then optionally applies fixes with verification.
feature
Full per-feature pipeline: implement → testloop → evaluator challenge → coder feedback → document → commit.
quick
/quick — Lightweight Feature Workflow.
git-commit
Conventional Commits format for git commits and PR/MR titles. Type prefixes, scope rules, breaking change syntax, and commit message structure. Use when committing changes, writing commit messages, creating PR/MR titles, or formatting squash merge messages. Not for PR workflows (git-pr), CI/CD status (git-ci), or git…
wrap-up-branch
Finish a feature branch: add missing tests, review and fix the code, align docs, then merge only after explicit confirmation.