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 owainlewis/blueprint --skill task-to-prgit clone --depth 1 https://github.com/owainlewis/blueprintWrote 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/owainlewis/blueprint/task-to-pr)<a href="https://agentmods.dev/skills/owainlewis/blueprint/task-to-pr"><img src="https://agentmods.dev/badge/skills/owainlewis/blueprint/task-to-pr/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/owainlewis/blueprint/task-to-pr"><img src="https://agentmods.dev/badge/skills/owainlewis/blueprint/task-to-pr.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00038 | $0.00955 |
| Opus 5.5 | $0.00015 | $0.00382 |
| Sonnet 5.5 | $0.00008 | $0.00191 |
| Haiku 4.5 | $0.00004 | $0.00096 |
Grade A, and why
task-to-pr 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 11d 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Task to PR
Deliver each task as one focused pull request with proof. The spec is the ticket; accept a Markdown spec, GitHub issue, or decided task with acceptance checks. Do not create a second work definition.
Read required skills directly from their SKILL.md files as instructions for this workflow. Do not invoke them through a skill command that the client blocks.
Prepare
- Read the source, repository instructions, relevant requirements and architecture, code, and tests. Reuse an existing branch, worktree, and pull request when continuing work.
- Confirm the outcome, scope, decisions, and checks are sufficient. If a consequential choice is missing, return to
/specor report the needed decision before implementing. Do not write specs for small, decided work. - Split larger specs with
/planwhen useful. Each task delivers one working result. Identify dependencies and start independent work together when useful.
Deliver and repair
- Create or reuse an isolated branch and worktree. Start independent work from the latest remote default branch. Follow repository naming and worktree rules.
- Implement the task and meaningful tests for changed behavior and affected failures. Update requirements, architecture, and the spec when the change affects them. Keep intended architecture and implementation status accurate.
- Use
/testto prove acceptance and affected rules. Fix failures before committing. - Create a Conventional Commit, push, and open or update the pull request. Follow the repository PR template. Lead with the problem and result; include proof and the source link. Mark it ready for review and move a tracker ticket to Review when supported.
- Use
/reviewwith a fresh subagent that did not implement the change. Wait for configured CI and automated review on the current commit. - Fix valid findings and failures caused by the change. Reply to review findings with the fix or evidence for making no change. Resolve a thread only when fully addressed.
- After changing the implementation, repeat affected
/testchecks and fresh/review, commit, push, and wait for CI and automated review again. Update PR proof. Continue until all available checks pass and no actionable finding remains. - Report a blocker when progress requires a missing decision, permission, unavailable check, or external repair. Do not weaken tests, bypass repository rules, or claim unrun checks passed.
- Record final proof and the PR link in the source spec or task. Update delivery status to reflect the actual result, including whether the PR is open or merged. Update the original tracker item when one exists. Leave passing PRs open for human review by default. Pending human approval is a merge blocker, not a failed implementation check.
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.
- 11d ago Changed · +3 lines af725f61d414
- 17d ago Changed · -3 lines · -5 tokens per session 6f86088f06c0
- 1mo ago First seen · 68 lines · 43 tokens per session scan A 31e23dcb2aba
task-to-pr is a skill published in the GitHub repository owainlewis/blueprint (419 stars, last pushed 7d ago), licensed MIT. It adds 38 tokens to every session and 955 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 2026-08-30.
Other skills, from other repositories
check
Reviews diffs, PRs, release readiness, and publishing follow-through. Use when asked to review, triage issues or PRs, or ship. Not for debugging root causes or prose.
antfu-create-pr
Create a reviewable GitHub pull request from the current branch with a Conventional Commits title, a concise evidence-based body, and before/after screenshots for UI changes. Use when asked to open, create, publish, or prepare a PR.
gsd-pr-branch
Create a clean PR branch by filtering out .planning/ commits — ready for code review.
factory-babysit-pr
Experimental workflow for babysitting one explicitly authorized pull or merge request. Use to monitor its live review state and checks, fix actionable in-scope findings, and apply separate reply, approval, merge, and soak gates.
factory-review-prs
Experimental workflow for reviewing configured repositories' pull requests. Use for manual or scheduled PR triage, approval, or merge decisions.
comet-github-pr-review
A read-only review process for pull requests in Comet's GitHub repositories. A pull request is a proposed code change; the review checks its current code, related issue, comments, merge status, and automated checks.