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 s977043/PlanGate --skill pr-decisiongit clone --depth 1 https://github.com/s977043/PlanGateWrote 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/s977043/plangate/pr-decision)<a href="https://agentmods.dev/skills/s977043/plangate/pr-decision"><img src="https://agentmods.dev/badge/skills/s977043/plangate/pr-decision.svg" alt="Measured on agentmods" 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 | $0.00053 | $0.01985 |
| Opus 5 | $0.00026 | $0.00992 |
| Sonnet 5 | $0.00011 | $0.00397 |
| Haiku 4.5 | $0.00005 | $0.00198 |
Grade A, and why
pr-decision 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.
How it starts
The opening of the file, as written. The whole thing — 243 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR Decision Skill
Evidence Ledger + Review Gate + GateStatus + Rollback Plan の状態から PR 可否を判定し、 判定根拠を structured output で出力する。
Iron Law
NO PR WITHOUT EVIDENCE-BASED GATE PASSAGE
証拠なしの PR 作成を防ぐ。全ての Gate が通過していることを確認してから PR を作成する。
入力(5 つ)
- Gate Status: Completion Gate の
checksオブジェクト(PASSED / BLOCKED) - Evidence Status: EvidenceLedger の
status(passed / failed / skipped) - Review Findings: Review Gate の finding 一覧(severity 付き)
- Unresolved Risks:
plan.mdの Risks & Mitigations で未解決のもの - Rollback Plan: 存在するか、内容は適切か
出力: PR 判定レポート
## PR 判定レポート
### 判定: {APPROVE | BLOCK | CONDITIONAL}
### Gate Status
| Gate | 状態 |
|------|------|
| Design Gate | {passed / blocked / skipped} |
| TDD Gate | {passed / blocked / skipped} |
| Review Gate | {passed / blocked / skipped} |
| Completion Gate | {PASSED / BLOCKED} |
### Evidence Status
- Overall: {passed / failed / skipped}
- Missing: {欠落している証拠(なければ "なし")}
### Review Findings サマリ
| Severity | 件数 |
|----------|------|
| critical | {N} |
| major | {N} |
| minor | {N} |
| info | {N} |
### Unresolved Risks
- {未解決リスクのリスト(なければ "なし")}
### Rollback Plan
- 存在: {あり / なし}
- 内容の妥当性: {適切 / 不足}
### 判定根拠
{判定理由を 3〜5 行で記述}
### アクション
- {次のアクション(マージ可能 / 修正が必要な項目)}
判定基準
| 判定 | 条件 |
|---|---|
| APPROVE | Completion Gate PASSED + Evidence Ledger passed + critical finding = 0 + Rollback Plan あり(critical モード) |
| BLOCK | Completion Gate BLOCKED、または critical finding >= 1、または Evidence Ledger failed |
| CONDITIONAL | major finding >= 1 かつ critical = 0、または minor リスクが残存 → 条件付き承認(担当者の判断) |
手順
Step 1: 入力収集
以下の形式で入力を収集する:
{
"gateStatus": {
"completionGate": "PASSED | BLOCKED",
"checks": {
"designGate": "passed | blocked | skipped",
"tddEvidence": "passed | blocked | skipped",
"reviewGate": "passed | blocked | skipped",
"evidenceLedger": "passed | blocked | skipped",
"humanApproval": "passed | blocked | skipped",
"rollbackPlan": "passed | n/a | blocked"
}
},
"evidenceStatus": {
"status": "passed | failed | skipped",
"missingEvidence": ["<欠落している証拠>"]
},
"reviewFindings": [
{
"severity": "critical | major | minor | info",
"description": "<finding の説明>",
"resolved": true
}
],
"unresolvedRisks": ["<未解決リスクの説明>"],
"rollbackPlan": {
"exists": true,
"adequate": true
}
}
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 · 243 lines · 53 tokens per session scan A 61256c70e457
pr-decision is a skill published in the GitHub repository s977043/PlanGate (2 stars, last pushed yesterday), licensed MIT. It adds 53 tokens to every session and 1,985 once invoked, about $0.0003 per session on Opus 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
05-review
Review a diff read-only on three axes, code, behavior versus the plan, and relevancy, into one verdict report. Use before shipping a change. Not for fixing findings or auditing a codebase.
github-pr-comment
Post one exact GitHub pull-request comment through local gh, any compatible hosted connector, or the explicit human-gated MCP composition, with retry safety and independent readback.
pr-reviewing
Review a PR across multiple dimensions — description, code changes, code scan, unit tests — using parallel subagents. Supports GitHub, GitLab, and enterprise platforms.
finishing-a-development-branch
The terminal step of /feature and /sprint. Routed to once commit-gate has cleared, to decide the branch's fate — merge via PR, open a PR, or discard. Direct merge to the default branch is forbidden; every change lands through a PR. Under /sprint the skill auto-selects "open PR" and surfaces the merge decision to the…
requesting-code-review
Use at executor review checkpoints to dispatch the code-reviewer agent with structured context — git range, workflow contracts, and verification evidence.
ca-pr
Open a pull request the only sanctioned way — clear every BLOCK-level review finding, then stage the PR. Never a direct write to the default branch.