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 onsager-ai/dev-skills --skill pr-lifecyclegit clone --depth 1 https://github.com/onsager-ai/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/onsager-ai/dev-skills/pr-lifecycle)<a href="https://agentmods.dev/skills/onsager-ai/dev-skills/pr-lifecycle"><img src="https://agentmods.dev/badge/skills/onsager-ai/dev-skills/pr-lifecycle/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/onsager-ai/dev-skills/pr-lifecycle"><img src="https://agentmods.dev/badge/skills/onsager-ai/dev-skills/pr-lifecycle.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 | $0.00046 | $0.01419 |
| Opus 5.5 | $0.00018 | $0.00568 |
| Sonnet 5.5 | $0.00009 | $0.00284 |
| Haiku 4.5 | $0.00005 | $0.00142 |
Grade A, and why
pr-lifecycle 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 3d 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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pull-request lifecycle
Scope
This skill owns PR method. The task and repository policy own publication, review responses, issue/comment writes and merge authority. AGENTS.md and the repo overlay own scope, labels, SDD linking and gates. Opening/updating authority does not itself authorize merging. Keep repository-specific policy out of this shared procedure.
Prerequisites
Know the exact repo, base/head and delivery scope. Follow pre-push before publication. Use harness-operations for capability mapping only when needed; subscriptions and a specific GitHub tool are not prerequisites.
Reviewable descriptions
Lead with the concrete problem and resulting behavior. Use a before/after example when it explains the change. Describe the final diff for a reviewer who has not seen the conversation; rewrite stale titles and bodies instead of appending a work diary. Keep a small change to a short paragraph plus validation. Aim for 100–250 words for most bodies, expanding only for material review complexity. Link detailed protocols, benchmark tables and historical command logs. Include only evidence that helps assess the change or its readiness.
For a larger change, use this order:
- Problem and outcome: state the trigger, previous behavior and new behavior.
- Changes: explain the decisions that affect behavior or review. Keep distinct concerns in separate PRs when they can be reviewed and validated independently.
- Review: name the first two or three authored files or groups to read. Identify generated bundles, screenshots and evidence separately from authored logic.
- Validation and remaining scope: give actual commands/results, their exact revision, linked evidence and unrun gates. State stack and cross-repository dependencies, including an exact source pin when adoption requires one.
Use short active sentences and consistent terms. Expand an unfamiliar acronym once. Keep identifiers exact. Separate numbers from words and state their units. Avoid vague claims such as "improve robustness" without the observable behavior. Plain technical English does not require a restricted dictionary or an STE compliance claim.
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.
- 3d ago Changed · +7 lines bd4bd6fbd8aa
- 12d ago Changed · +47 lines 7ef0eb8cc47e
- 15d ago Changed 41669b001109
- 18d ago Changed · -89 lines · -160 tokens per session 7b197389d51b
- 1mo ago First seen · 153 lines · 206 tokens per session scan A 2bd67d8097cc
pr-lifecycle is a skill published in the GitHub repository onsager-ai/dev-skills (7 stars, last pushed 3d ago), licensed MIT. It adds 46 tokens to every session and 1,419 once invoked, about $0.0002 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
Draft a PR body from OMC's paper trail — the smallest visual that proves the change, evidence consumed from the verify protocol (never re-collected), reversibility from the ADR test on the diff, glossary language throughout.
merge-batch
Prepare and merge an owner-selected PR batch with contributor credit and exact-candidate admission. Use for a pasted PR list; combined focused validation is diagnostic, and every actual landing still requires its applicable checks and authorization.
otto-pr-review-loop
Run Polly and OCR on a PR until all findings settle.
engram-branch-pr
PR creation workflow for Engram following the issue-first enforcement system. Trigger: When creating a pull request, opening a PR, or preparing changes for review.
verify-behavior
Verify or reproduce visible product behavior by driving the real UI with pi-computer-use's checked tools, requiring verified expect postconditions and durable state evidence for meaningful UI flows. Use when triage needs visual reproduction, implementation needs behavioral proof, review needs interactive confirmation…
github-contributor
A step-by-step guide for contributing code, tests, documentation, or build changes to open-source projects you do not maintain. It explains how to prepare a pull request that follows the project’s rules and is easier for maintainers to review.