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/sungurerdim/dev-skills/ds-commitnpx skills add sungurerdim/dev-skills --skill ds-commitgit clone --depth 1 https://github.com/sungurerdim/dev-skillsWhat 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 | $0.00036 | $0.04490 |
| Opus 5 | $0.00018 | $0.02245 |
| Sonnet 5 | $0.00007 | $0.00898 |
| Haiku 4.5 | $0.00004 | $0.00449 |
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 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 — 250 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 / needs-human); 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.
What ships with it
3 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.
- yesterday 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 6d ago), licensed MIT. It adds 36 tokens to every session and 4,490 once invoked, about $0.0002 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
ring:applying-composition-patterns
React composition patterns that scale. Avoid boolean prop proliferation by using compound components, lifting state, and composing internals. Use when refactoring components with boolean prop proliferation, building flexible component libraries, or during architecture review. Skip for simple components with 1-2 props…
ring:adopting-lib-commons-huma-wrapper
Adopting the lib-commons/v5 shared Huma (OAS 3.1) OpenAPI wrapper + RFC 9457 problem model (commons/net/http/{openapi,problem}) in a Lerian Go service: wire openapi.New/ServeSpec + problem.Install (central >=500 scrub) on BOTH runtime and spec-gen paths, the per-rail problem.MapError flex seam, and rename-only spec…
ring:searching-code
Forensic code search and analysis with optional Chain of Draft (CoD) ultra-concise mode. Five-phase methodology (clarification, planning, execution, analysis, synthesis) with severity assessment. Use for targeted investigation of specific patterns, bugs, or vulnerabilities. Skip for broad architecture mapping (use…
ring:opening-pull-requests
Open a GitHub Pull Request with automatic base branch detection, scope allowlist enforcement, PR template filling, and post-create base verification. Replaces ring:generating-pr-descriptions. Use after pushing a branch when ready to open a PR. Skip if the branch is not yet pushed or there are uncommitted changes …
ring:fixing-lint
Fixing lint to a clean state: runs the linter, groups reported issues into independent streams, and dispatches one parallel fixer agent per stream (ring:backend-go for Go, ring:general-purpose otherwise), iterating until clean. Use when a codebase has lint errors across multiple files. Skip for a single error (fix…
ring:cleaning-comments
Cleaning redundant and obvious comments following clean code principles while preserving meaningful documentation. Supports git scope filtering (staged, unstaged, branch, commit-range). Use when code has excessive comments, during code review, or post-refactor cleanup. Skip when reviewing documentation files or…