pr-decision

pr-decision is a skill for Claude Code, Codex from s977043/PlanGate. It costs 53 tokens per session (1,985 once invoked), scanned A, original, MIT.

A decision-making recipe for deciding whether a code change is ready to become a pull request, based on evidence, review results, risks, checks, and a rollback plan. A pull request is a proposed change that others review before it is added to a codebase.

In plain words
What is it for?
It is for producing a structured approve, block, or conditional decision report. It checks gate statuses, evidence, review findings, unresolved risks, and whether a suitable rollback plan exists.
Why use it?
It prevents a pull request from being approved without the required checks and supporting evidence. It also makes missing reviews, unresolved risks, and recovery steps visible.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents); mentions Codex.

Good fit It is for producing a structured approve, block, or conditional decision report. It checks gate statuses, evidence, review findings, unresolved risks, and whether a suitable rollback plan exists.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/s977043/plangate/pr-decision
Install

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.

Any agent
npx skills add s977043/PlanGate --skill pr-decision
Clone the repo
git clone --depth 1 https://github.com/s977043/PlanGate

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for pr-decision

README.md
[![agentmods](https://agentmods.dev/badge/skills/s977043/plangate/pr-decision.svg)](https://agentmods.dev/skills/s977043/plangate/pr-decision)
Your own site
<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>
Per session 53 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,985 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 7d ago against content hash 61256c70e457, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

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.

.agents/skills/pr-decision/SKILL.md · 243 lines

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)

  1. Gate Status: Completion Gate の checks オブジェクト(PASSED / BLOCKED)
  2. Evidence Status: EvidenceLedger の status(passed / failed / skipped)
  3. Review Findings: Review Gate の finding 一覧(severity 付き)
  4. Unresolved Risks: plan.md の Risks & Mitigations で未解決のもの
  5. 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
  }
}

Read the full file on GitHub · 243 lines

Changes

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.

  1. 7d ago First seen · 243 lines · 53 tokens per session scan A 61256c70e457

Subscribe to this mod's changes

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.

Related

Other skills, from other repositories