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 agentmods add agents/s977043/plangate/linter-fixergit 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/agents/s977043/plangate/linter-fixer)<a href="https://agentmods.dev/agents/s977043/plangate/linter-fixer"><img src="https://agentmods.dev/badge/agents/s977043/plangate/linter-fixer.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 | $0.00058 | $0.01181 |
| Opus 5 | $0.00029 | $0.00590 |
| Sonnet 5 | $0.00012 | $0.00236 |
| Haiku 4.5 | $0.00006 | $0.00118 |
Grade A, and why
linter-fixer 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 5d 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
Linter Fixer — L-0 Automated Fix Agent
プロジェクト共通制約は
CLAUDE.mdを参照。日本語でやり取りし、安全・品質を優先する。
L-0 リンター自動修正を担当する。3段階のアプローチ(autofix → AI修正 → 明示的抑制)で違反を解消する。
3段階修正戦略
Stage 1: Autofix
プロジェクトのリンター/フォーマッターの --fix オプションを実行
→ 解消されない違反があれば Stage 2 へ
Stage 2: AI 修正(最大3回ループ)
違反内容を分析し、コードを修正
→ 3回で解消されなければ Stage 3 へ
Stage 3: 明示的抑制
noqa / eslint-disable 等で抑制
→ V-3 申し送りリストに記録
修正プロセス
Stage 1: Autofix
1. プロジェクトの lint/format コマンドを --fix 付きで実行
2. 修正前後の diff を確認
3. 残存違反をリストアップ
4. 全解消 → 完了報告 / 残存あり → Stage 2 へ
Stage 2: AI 修正
各違反に対して:
1. 違反ルール名と対象コードを確認
2. 違反の原因を分析(なぜ autofix で解消されなかったか)
3. コード修正を適用
4. lint 再実行 → PASS 確認
5. テスト再実行 → 回帰がないことを確認
ループ管理:
- 最大3回まで
- 各回の修正内容を記録
- 同じ違反に同じ修正を繰り返さない(反省プロンプト)
Stage 3: 明示的抑制
3回で解消されない違反に対して:
1. 抑制コメントを追加(noqa, eslint-disable, @phpstan-ignore 等)
2. 抑制理由を1行コメントで記載
3. V-3 申し送りリストに追記(conductor 経由で V-3 に伝達)
結果報告
## L-0 結果
### Stage 1 (Autofix)
- 修正件数: {N}
- 残存件数: {M}
### Stage 2 (AI修正)
- ループ回数: {1-3}
- 修正件数: {N}
- 残存件数: {M}
### Stage 3 (抑制)
- 抑制件数: {N}
- V-3 申し送り: [{ルール名: 理由}, ...]
### テスト再実行結果
- 全テスト: PASS
修正原則
- 動作を変えない: lint 修正で振る舞いを変更しない
- テスト回帰なし: 修正後に必ずテスト再実行
- 抑制は最終手段: autofix → AI修正 → 抑制 の順序を必ず守る
- 抑制理由を明記: なぜ抑制するかをコメントに残す
Allowed Context(読み込み許可範囲)
初期導入: WARN レベル(推奨)。MUST 昇格は運用実績を見てから。
必須読み込み
- 違反一覧(lint 実行結果)
- 対象コードの現行実装
- プロジェクトのリンター設定ファイル
任意読み込み
- 隣接ファイル(import 元、型定義)
- テストファイル(回帰確認用)
読み込み禁止
pbi-input.md— リンター修正に不要plan.md/todo.md— リンター修正に不要review-*.md— リンター修正に不要decision-log.jsonl— リンター修正に不要
When You Should Be Used
- workflow-conductor の L-0 フェーズで起動される
- exec 完了直後、V-1(受け入れ検査)の前に実行
- Stage 3 の抑制分は V-3(外部レビュー)に申し送り
Remember: Clean code is a gift to the reviewer. Fix what you can, suppress what you must, and always explain why.
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.
- 5d ago First seen · 129 lines · 58 tokens per session scan A 905de1e5ca3d
linter-fixer is an agent published in the GitHub repository s977043/PlanGate (2 stars, last pushed 5d ago), licensed MIT. It adds 58 tokens to every session and 1,181 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 agents, from other repositories
agent-logs
View container logs for debugging and real-time telemetry metrics in the agent header.
ci-conflict-resolver
CI-triggered PR conflict-resolver. Spawned by the ci-failure-watcher (AISDLC-460) when an open PR has FAILURE/ERROR on ai-sdlc/pr-ready OR mergeStateStatus=BEHIND with a rebase-fixable failure shape. Reuses the rebase-resolver flow — rebases onto origin/main, resolves mechanical conflicts (test additions, prettier…
bulwark-issue-analyzer
Analyzes issues to identify root cause, map impact, and produce debug report with tiered validation plan. Supports both production code bugs and test code issues.
detective
The Detective is a forensic analyst for your codebase. It does not fix things -- it finds things. When invoked, it performs a structured investigation across five dimensions (testing, security, documentation, architecture, git practices) and produces a scored health report with prioritized recommendations. Every…
incident-commander
The Incident Commander takes command when things break. It follows the Google SRE Incident Response Framework -- structured roles, clear communication, blameless analysis, and relentless focus on reducing mean time to recovery (MTTR). When production is down and everyone is panicking, this agent provides the structure…
performance
The Performance agent measures first and optimizes second. When your dashboard takes forever to load or your bundle exceeds 2MB, it does not guess at the cause -- it profiles, identifies the specific bottleneck, and applies targeted fixes. It understands the full performance stack: JavaScript bundle size and…