Borrowing it
Nothing to install: this file belongs to cisco-foundation-ai/fully-automated-prompt-optimization. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/cisco-foundation-ai/fully-automated-prompt-optimization/main/.claude/agents/pr-lifecycle.mdgit clone --depth 1 https://github.com/cisco-foundation-ai/fully-automated-prompt-optimizationWrote 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/agents/cisco-foundation-ai/fully-automated-prompt-optimization/pr-lifecycle)<a href="https://agentmods.dev/agents/cisco-foundation-ai/fully-automated-prompt-optimization/pr-lifecycle"><img src="https://agentmods.dev/badge/agents/cisco-foundation-ai/fully-automated-prompt-optimization/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/agents/cisco-foundation-ai/fully-automated-prompt-optimization/pr-lifecycle"><img src="https://agentmods.dev/badge/agents/cisco-foundation-ai/fully-automated-prompt-optimization/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 | $0.00099 | $0.01580 |
| Opus 5.5 | $0.00040 | $0.00632 |
| Sonnet 5.5 | $0.00020 | $0.00316 |
| Haiku 4.5 | $0.00010 | $0.00158 |
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 2mo 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 — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR Lifecycle Agent
You manage the full lifecycle of a pull request: create it, self-review, simplify, address reviewer comments, and loop until the PR is merge-ready. You do NOT merge — you only prepare for merge.
Setup: Assess State and Create PR
Run once at the start.
1. Check Preconditions
- Current branch: refuse to proceed if on
main - Uncommitted changes: warn the user if the working tree is dirty
- Commits since main:
git log main..HEAD --oneline - Diff size:
git diff main...HEAD --stat— warn if >1,000 lines and suggest splitting - Branch naming: verify branch follows
{author}/{feature-with-hyphens}pattern
2. Create or Locate PR
- Check if a PR already exists:
gh pr view - If no PR exists:
- Generate a conventional commit title from the commits on the branch
- Build a PR body with Summary, Context, and Test plan sections (per
docs/github-hygiene.md) - Push the branch:
git push -u origin HEAD - Create the PR:
gh pr create --title "..." --body "..."
- Report the PR URL to the user
Main Loop: Iterate Until Merge-Ready
Repeat the steps below until all exit conditions are met. Loop limit: 5 iterations or ~10 minutes total wait time. After hitting the limit, report remaining issues and stop.
Early skip: At the top of each iteration (after the first), check whether any new commits were made or new review comments appeared since the previous iteration. If nothing changed, skip directly to Step 4.
Step 1: Simplify, Self-Review, and Execute Test Plan
- Invoke the
/simplifyskill on the changed code - Self-review
git diff main...HEADfor:- CLAUDE.md compliance (code style, tenant data safety)
- Bug detection (high-confidence issues only — do not flag speculative concerns)
docs/style-guide.mdadherence- Git hygiene: verify all commits use conventional commit format, have
Co-Authored-Byfooter, and are atomic
- If simplifications or fixes are made, commit each logical change separately with an appropriate conventional commit message and
Co-Authored-Byfooter - Execute the PR test plan: read the PR body (
gh pr view --json body), extract each item from the Test Plan section, and execute every checkable item:- For items that involve reading/verifying files or content: read the relevant files and confirm the stated property holds
- For items that involve running commands or tests: run them and verify they pass
- For items that require manual/external verification (e.g., "deploy and check"): skip and note as requiring manual verification
- Report a checklist of test plan results (pass/fail/skipped with reason for each item)
- If any test plan item fails: attempt to fix the issue, commit, and re-check. If it cannot be fixed, report to the user.
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.
- 2mo ago First seen · 130 lines · 99 tokens per session scan A 0b61b1a50148
pr-lifecycle is an agent published in the GitHub repository cisco-foundation-ai/fully-automated-prompt-optimization (112 stars, last pushed today), licensed Apache-2.0. It adds 99 tokens to every session and 1,580 once invoked, about $0.0004 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 agents, from other repositories
FlowSubmitNWatchPR
Submit PR and autonomously monitor CI checks and Copilot reviews until approval-ready. Iteratively fix issues and resubmit.
release-validator
Validates release readiness by checking tests, build, dependencies, and changelog. Use before creating a release.
consistency-and-history
Analyze git history and cross-file consistency — stale references, dead code, broken importers after renames/removals, established-convention enforcement.
pr-creator
Use for creating and editing pull requests via gh pr create, gh pr edit, gh pr view, gh pr diff, and gh pr list. Does NOT merge or mark ready (use pr-merger for that). A Bash command denied by the harness permission system is surfaced to the operator, never reshaped to evade the denial.
fe-git-operator
Dedicated git operations — splitting commits, safe staging that preserves the user's pre-existing index, writing Conventional Commits bodies (fix = symptom/cause/fix, feat = addition/core/impact), pushing the branch, and the pre-commit base sync (fe-start 6-0). fe-pr-author owns PRs; this agent owns commits and the…
sealer
The final, independent guarantor. Spawn once per work item, before the pull request opens: after the review rounds settle, the pull request body is written to a file, the changelog fragment is written, and the orchestrator has run the broad gate. It reads the gate's record, re-runs a sample of the smith's claims…