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 yarlson/yarstack --skill phase-commitgit clone --depth 1 https://github.com/yarlson/yarstackWrote 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/yarlson/yarstack/phase-commit)<a href="https://agentmods.dev/skills/yarlson/yarstack/phase-commit"><img src="https://agentmods.dev/badge/skills/yarlson/yarstack/phase-commit.svg" alt="Measured on agentmods" 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 | $0.00264 |
| Opus 5 | $0.00018 | $0.00132 |
| Sonnet 5 | $0.00007 | $0.00053 |
| Haiku 4.5 | $0.00004 | $0.00026 |
Grade A, and why
phase-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 7d 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.
What it actually says
Phase Commit
Create one isolated local commit without changing history or external state.
Workflow
- Confirm required repository checks and applicable validation and review cover the exact intended content.
- Inspect status, staged and unstaged changes, and relevant untracked files; preserve all unrelated user work.
- Stop when scope is ambiguous or includes sensitive, unexpectedly generated, or otherwise unsafe paths.
- Stage only explicit paths with
git add -- <paths>; never use broad staging commands or globs. - Review the staged path list and diff against the requested unit.
- Draft the commit subject and body using repository conventions, then use
text-improvewithout changing technical meaning. - Commit without bypassing hooks or changing signing policy.
- Verify the created commit content and remaining worktree.
Do not amend, rewrite history, push, create branches or pull requests, manage CI, tag, release, or include unrelated changes.
On hook or commit failure, stop and report the blocker without claiming completion.
Finish only after verifying the created commit, then report its hash and concise summary.
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.
- 7d ago First seen · 26 lines · 36 tokens per session scan A 73189c72ead4
phase-commit is a skill published in the GitHub repository yarlson/yarstack (3 stars, last pushed yesterday), licensed MIT. It adds 36 tokens to every session and 264 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
work-unit-commits
Plan commits as reviewable work units. Trigger: implementation, commit splitting, chained PRs, or keeping tests and docs with code.
plate
Turn finished local work into a commit, an ordinary pull request, or a pull request stack. Use this skill to commit changes or to publish a branch. Use it to open or update a pull request. Use it to create, sync, restack, or submit a pull request stack. You can also run /plate. This skill owns all staging, commits…
requesting-code-review
Use when implementation is done and you need a structured pre-PR review workflow. Triggers: 'ready for review', 'review my changes before PR', 'pre-merge check', 'is this ready', 'submit for review'. NOT for: post-merge review (use code-review) or deciding how to integrate (use finishing-a-development-branch).
owndiff-pre-commit
Audit OwnDiff changes before committing or releasing by checking scope, generated artifacts, private data, documentation accuracy, version consistency, structured files, tests, and the OwnDiff ownership gate. Use when a user asks to verify, clean up, prepare, commit, publish, or release changes in the OwnDiff…
create-commit
Create a git commit whose message records why the change exists, not just what changed. Stages only the files that belong to the change, matches the repo's existing commit style, and shows the message and staged files for user approval before committing. Use when asked to commit work or write a commit message.…
standalone-pr-loop
Implement same-repository GitHub Issues into a reviewed pull request, or review and fix an existing PR, iterating with fresh independent read-only native subagents selected adaptively from the change risk until no actionable feedback remains. Use for issue-to-PR implementation or iterative PR review/fix work.