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.
git clone --depth 1 https://github.com/jpoley/flowspecWrote 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/jpoley/flowspec/flow.submit-n-watch-pr)<a href="https://agentmods.dev/agents/jpoley/flowspec/flow.submit-n-watch-pr"><img src="https://agentmods.dev/badge/agents/jpoley/flowspec/flow.submit-n-watch-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/agents/jpoley/flowspec/flow.submit-n-watch-pr"><img src="https://agentmods.dev/badge/agents/jpoley/flowspec/flow.submit-n-watch-pr.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 | $0.00030 | $0.00592 |
| Opus 5.5 | $0.00012 | $0.00237 |
| Sonnet 5.5 | $0.00006 | $0.00118 |
| Haiku 4.5 | $0.00003 | $0.00059 |
Grade A, and why
FlowSubmitNWatchPR 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
/flow:submit-n-watch-pr - Autonomous PR Management
Submit a PR and autonomously monitor CI checks and code review feedback until approval-ready.
User Input
$ARGUMENTS
You MUST consider the user input before proceeding (if not empty).
Critical Success Criteria
Your PR is ONLY ready for merge when you see BOTH:
- All CI checks pass (green checkmarks)
- Zero Copilot review comments or all addressed
Instructions
Prerequisites:
- Run
/flow:validatefirst to ensure quality - All local tests pass
- Branch is rebased from main
Workflow:
Step 1: Pre-Submit Validation
# Verify branch is up to date
git fetch origin main
git rebase origin/main
# Run final validation
uv run ruff check .
uv run pytest tests/ -x -q
Step 2: Create PR
# Push branch
git push origin $(git branch --show-current)
# Create PR with proper description
gh pr create \
--title "feat(scope): description" \
--body "## Summary\n- Change 1\n- Change 2\n\n## Test Plan\n- [ ] Test 1\n- [ ] Test 2"
Step 3: Monitor and Iterate
- Wait for CI checks to complete
- Check for Copilot review comments:
gh pr view --comments - If issues found:
- Fix the issues locally
- Push updates:
git push - Wait for re-check
- Repeat until all checks pass and no comments remain
Step 4: Request Review
# When ready, request human review
gh pr ready
gh pr edit --add-reviewer <reviewer>
Key Commands:
# Check PR status
gh pr status
gh pr checks
# View review comments
gh pr view --comments
# Update PR after fixes
git add .
git commit --amend --no-edit
git push --force-with-lease
Exit Conditions:
- All CI checks green
- Zero unresolved Copilot comments
- PR marked ready for review
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 · 102 lines · 30 tokens per session scan A 47a3e5830a65
FlowSubmitNWatchPR is an agent published in the GitHub repository jpoley/flowspec (50 stars, last pushed 6d ago), licensed Apache-2.0. It adds 30 tokens to every session and 592 once invoked, about $0.0001 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 2026-10-09.
Other agents, from other repositories
release-validator
Validates release readiness by checking tests, build, dependencies, and changelog. Use before creating a release.
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.
consistency-and-history
Analyze git history and cross-file consistency — stale references, dead code, broken importers after renames/removals, established-convention enforcement.
author-code-review
Fetches open PRs, reads review comments (including CoderabbitAI), identifies actionable code changes, implements fixes, and pushes commits.
sealer
The one broad run. Spawn after the review rounds settle and before the draft pull request is marked ready: it runs the repository's broad command and the plugin's own checks through broad-gate, reports what they said, and writes the last round record's Broad gate cell. It judges nothing.
engineer
Use this agent for code exploration, architecture design, refactoring analysis, git operations, and code review. Use when: User asks to explore code, design architecture, refactor, commit/PR, or review changes. Do NOT use when: User needs test generation (use qa-engineer), security audit (use security-scanner), or…