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 evidence-ledgergit 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/evidence-ledger)<a href="https://agentmods.dev/skills/s977043/plangate/evidence-ledger"><img src="https://agentmods.dev/badge/skills/s977043/plangate/evidence-ledger/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/s977043/plangate/evidence-ledger"><img src="https://agentmods.dev/badge/skills/s977043/plangate/evidence-ledger.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 | $0.00101 | $0.03152 |
| Opus 5 | $0.00051 | $0.01576 |
| Sonnet 5 | $0.00020 | $0.00630 |
| Haiku 4.5 | $0.00010 | $0.00315 |
Grade A, and why
evidence-ledger 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 — 270 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Evidence Ledger
完了主張を証拠付きで記録し、EvidenceLedger として出力する。
Iron Law
NO COMPLETION CLAIMS WITHOUT FRESH VERIFICATION EVIDENCE
「should work now」「probably fixed」「テスト通るはず」等の推測的完了宣言は禁止。 コマンド実行結果・終了コード・出力抜粋を証拠として記録せよ。
TDD 必須 mode では、単なる「テストが通った」だけでは不十分。 RED（期待通り失敗）→ GREEN（最小実装で成功）→ REFACTOR VERIFY（整理後も成功） の証跡を分けて記録する。
Common Rationalizations
| こう思ったら | 現実 |
|---|---|
| 「CIが通ったから証拠不要」 | CI はカバレッジの保証ではない。claim ごとに証拠を記録せよ |
| 「小さな修正だから証拠不要」 | 規模は関係ない。exitCode=0 を確認して記録せよ |
| 「レビューしたから大丈夫」 | review type の EvidenceItem として記録せよ |
| 「テストが通ったからTDD済み」 | GREENだけではTDD証跡にならない。REDの失敗理由も記録せよ |
| 「REDは見たがログは残していない」 | high-risk / critical では RED 証跡がなければ Completion Gate で block 対象 |
データスキーマ
EvidenceStatus
"passed" | "failed" | "skipped" | "unknown"
EvidenceType
"command" | "diff" | "test" | "review" | "manual"
EvidencePhase
phase は任意フィールド。ただし type="test" かつ TDD 証跡として使う場合は必須。
"tdd_red" | "tdd_green" | "refactor_verify" | "verification" | "baseline"
| phase | 用途 | 期待する exitCode |
|---|---|---|
baseline |
実装前の既存テスト確認 | 0 |
tdd_red |
failing test が期待通り失敗することの確認 | != 0 |
tdd_green |
最小実装で対象テストが成功することの確認 | 0 |
refactor_verify |
refactor後も対象テスト・関連検証が成功することの確認 | 0 |
verification |
TDD以外の通常検証 | 0 |
tdd_red の exitCode != 0 は失敗ではなく、期待されたRED証跡として扱う。ただし、conclusion には「なぜ期待通りの失敗と言えるか」を必ず書く。
EvidenceItem
{
"id": "string（例: ev-001）",
"type": "command | diff | test | review | manual",
"phase": "baseline | tdd_red | tdd_green | refactor_verify | verification（任意。TDD証跡では必須）",
"command": "string（type=command/test の場合）",
"exitCode": "number（type=command/test の場合）",
"outputExcerpt": "string（出力の一部抜粋）",
"filePath": "string（type=diff/test の場合）",
"reviewer": "string（type=review の場合）",
"conclusion": "string（必須 - この証拠から何が言えるか）",
"createdAt": "string（ISO 8601）"
}
EvidenceLedger
{
"claim": "string（完了したという主張）",
"status": "EvidenceStatus",
"evidence": "EvidenceItem[]",
"missingEvidence": "string[]（必須だが欠けている証拠の説明）"
}
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 · 270 lines · 101 tokens per session scan A 9961faa353aa
evidence-ledger is a skill published in the GitHub repository s977043/PlanGate (2 stars, last pushed today), licensed MIT. It adds 101 tokens to every session and 3,152 once invoked, about $0.0005 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
08-debug
Reproduce and fix a known bug, or find an unknown root cause by hypothesis validation. Use when the user wants to fix a bug, find why something breaks, or reopen a stuck investigation. Not for building a feature or reviewing a diff.
test-audit
Audit test suites for T1-T4 violations using AST analysis, mock detection, and multi-stage synthesis. Invoke when user asks to audit tests, check test quality, find mock violations, review test effectiveness, or inspect test suites for over-mocking. Triggers automatic rewrites when quality gates fail.
tdd
The test-first gate. Routed to by /feature (after the spec is approved), /fix, and /refactor before any implementation code is written. Six gated phases — obligation scan, red, green, obligation verify, coverage, lint. No feature code exists before Phase 1 clears; nothing reaches commit-gate until all six are green.
ca-feature
Start a feature: brainstorm a spec, get it approved, then drive it test-first through the pipeline. The one entry to implementation.
gsd-builder
Implement a design document end-to-end in a target repo by driving Claude Code through the GSD workflow — define a GSD milestone from the doc, then run /gsd-autonomous (TDD, skip-discuss) to build all phases unattended. Use when the operator hands you a design/spec document and asks to autonomously build, implement…
ca-fix
Fix a confirmed bug: a failing regression test first, then a minimal fix, then the rest of the tdd gates.