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 jleechanorg/agent-orchestrator-ts --skill pr-green-definitiongit clone --depth 1 https://github.com/jleechanorg/agent-orchestrator-tsWrote 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/jleechanorg/agent-orchestrator-ts/pr-green-definition)<a href="https://agentmods.dev/skills/jleechanorg/agent-orchestrator-ts/pr-green-definition"><img src="https://agentmods.dev/badge/skills/jleechanorg/agent-orchestrator-ts/pr-green-definition/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/jleechanorg/agent-orchestrator-ts/pr-green-definition"><img src="https://agentmods.dev/badge/skills/jleechanorg/agent-orchestrator-ts/pr-green-definition.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 | $0.00025 | $0.01404 |
| Opus 5.5 | $0.00010 | $0.00562 |
| Sonnet 5.5 | $0.00005 | $0.00281 |
| Haiku 4.5 | $0.00003 | $0.00140 |
Grade A, and why
pr-green-definition 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 9d 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR "Green" Definition (6-Green)
Was "7-Green" until this repo's own Skeptic PR-gating automation (skeptic-gate.yml, skeptic-cron.yml, test.yml's trigger job) was retired in PR #773 — Skeptic PASS is no longer a required gate here. See CLAUDE.md's "Skeptic Architecture" note for what still applies (consumer-repo templates, the ao skeptic verify CLI itself).
A PR is "green" (merge-ready) when all 6 conditions hold:
| # | Condition | Verification |
|---|---|---|
| 1 | CI passing | All checks show SUCCESS |
| 2 | No merge conflicts | mergeable: MERGEABLE |
| 3 | CodeRabbit APPROVED | CR must post explicit APPROVED review state (configured via .coderabbit.yaml approve=true); COMMENTED alone does not pass |
| 4 | Bugbot clean | Zero error-severity comments from cursor[bot] |
| 5 | All inline comments resolved | Zero unresolved non-nit inline review comments |
| 6 | Evidence review passed | evidence-review-bot APPROVED or evidence-gate CI passed |
Pre-merge verification is MANDATORY. Before executing any merge command (gh pr merge, gh api .../merge), verify all 6 gates pass. If ANY gate fails, do NOT merge — fix the failing gate first. Merging a non-green PR is a commitment integrity violation.
Verification Procedure (Mandatory)
WARNING: gh pr checks is NOT sufficient for 6-green verification. The Green Gate workflow always exits 0 (success), so gh pr checks shows "Green Gate: pass" even when individual gates FAIL. The "CodeRabbit: pass" line means the webhook responded, NOT that CodeRabbit gave an APPROVED review.
Step-by-step verification
Given a PR number N and its branch name BRANCH:
# 1. Get branch name
BRANCH=$(gh pr view N --repo OWNER/REPO --json headRefName --jq '.headRefName')
# 2. Get latest Green Gate run ID (use workflow file name to avoid ambiguity)
RUN_ID=$(gh run list --workflow green-gate.yml --repo OWNER/REPO --branch "$BRANCH" -L 1 --json databaseId --jq '.[0].databaseId')
# 3. Read gate-by-gate results (THE ONLY RELIABLE CHECK)
gh run view "$RUN_ID" --repo OWNER/REPO --log 2>/dev/null | grep -E "GATE-[1-5] (PASS|FAIL)"
# 4. Cross-reference CR review state (do NOT trust gh pr checks)
gh pr view N --repo OWNER/REPO --json reviews --jq '[.reviews[] | select(.state != "COMMENTED") | {author: .author.login, state: .state}] | last'
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.
- 9d ago First seen · 92 lines · 25 tokens per session scan A e7cf612a7b88
pr-green-definition is a skill published in the GitHub repository jleechanorg/agent-orchestrator-ts (8 stars, last pushed 3d ago), licensed MIT. It adds 25 tokens to every session and 1,404 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 2026-10-02.
Other skills, from other repositories
review-implement-phase
Implements triaged review actions, commits focused fixes, and posts Done plus resolves threads. Use when the user wants only the implementation phase of the review-framework workflow.
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.
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.
revdiff
Review diffs, files, and documents with inline annotations in a TUI overlay, or answer questions about revdiff usage, configuration, themes, and keybindings. Opens revdiff in agterm/tmux/zellij/herdr/kitty/wezterm/cmux/ghostty/iterm2/emacs-vterm, captures annotations, and addresses them. Works in git, hg, and jj repos…