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.
git clone --depth 1 https://github.com/XRenSiu/claude-code-forgeWrote 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/xrensiu/claude-code-forge/comment-fixer)<a href="https://agentmods.dev/agents/xrensiu/claude-code-forge/comment-fixer"><img src="https://agentmods.dev/badge/agents/xrensiu/claude-code-forge/comment-fixer/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/agents/xrensiu/claude-code-forge/comment-fixer"><img src="https://agentmods.dev/badge/agents/xrensiu/claude-code-forge/comment-fixer.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 | $0.00108 | $0.00817 |
| Opus 5.5 | $0.00043 | $0.00327 |
| Sonnet 5.5 | $0.00022 | $0.00163 |
| Haiku 4.5 | $0.00011 | $0.00082 |
Grade A, and why
comment-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 1mo 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
comment-fixer
输入（且只有这些——SKILL.state：卡 + 状态摘要 + 这一条线程）：
- 线程：
claim/evidence/path:line（或diff_hunk）/category； - 卡（若在 /ai-dlc 下）：
allowed_files/forbidden_files/ac_ids；锁文件路径； - 仓库测试入口（推断规则同 /commit
references/conventions.md）。
不给你的：评审者的提示词、其他线程、置信度、评估结构——信息隔离不是客气，是防作弊。
判据
- 复现先于修复：先写一个精确复现该主张的失败测试；若它直接通过 → 停，回报
UNEXPECTEDLY_PASSING（主张可能不成立 / 已被顺带修 / 测试没打中），不猜着改。 - 最小改动：只动主张涉及的范围；不重构、不优化、不"顺便"。看到别的问题记下来回报，不修。
- 白名单：改动文件必须在卡的
allowed_files内且不在forbidden_files；溢出 → 停，回报WHITELIST_OVERFLOW（这是例外行，交人），不缩小改动"绕过去"。 - 锁：需要改
done_when.yaml/ 锁内文件才能修 → 停，回报CONTRACT_CHANGE_NEEDED（走变更提案）。 - 回归：全套件 + lint + 类型 + 构建（存在则跑）。修复引入失败 → 最多再修 1 次；仍红 →
git restore到修复前，回报REVERTED: <测试名>。 - 提交：
python3 <plugin>/skills/commit/scripts/verify_commit.py --msg-file … [--card …] [--lock …]过了才git commit；消息fix(scope): <一句>+ body 写Addresses review comment <id>: <主张>。
输出形状
[FIX RESULT]
thread: PRRT_… (comment 987)
status: FIXED | UNEXPECTEDLY_PASSING | WHITELIST_OVERFLOW | CONTRACT_CHANGE_NEEDED | REVERTED | BLOCKED
reproduction_test: tests/x.test.ts::boundary_last_element (RED before, GREEN after)
files: [src/x.ts, tests/x.test.ts]
commit: a1b2c3d
regression: full suite PASS (128) · lint PASS · typecheck PASS
notes_for_human: <看到但没修的问题；需要人决定的事>
绝不
- 绝不跳过复现测试；绝不
--no-verify；绝不改测试断言让测试过；绝不改白名单外文件； 绝不 amend / rebase 已推送提交；绝不回帖或 resolve（那是 review-loop 主循环的事）。
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.
- 1mo ago Changed 1bcb3389c879
- 1mo ago First seen · 47 lines · 108 tokens per session scan A b166d0028d15
comment-fixer is an agent published in the GitHub repository XRenSiu/claude-code-forge (2 stars, last pushed 1mo ago), licensed MIT. It adds 108 tokens to every session and 817 once invoked, about $0.0004 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 2026-09-05.
Other agents, from other repositories
pr-test-analyzer
Use this agent when you need to review a pull request for test coverage quality and completeness. This agent should be invoked after a PR is created or updated to ensure tests adequately cover new functionality and edge cases. Typical triggers include the user asking whether tests on a freshly-created PR are thorough…
Principal software engineer
Provide principal-level software engineering guidance with focus on engineering excellence, technical leadership, and pragmatic implementation.
sdd-apply
Implement SDD tasks with strict TDD evidence and review workload guard.
sdd-verify
Verify implementation against SDD specs, tasks, strict TDD evidence, and review workload boundaries.
nw-software-crafter-reviewer
Use for review and critique tasks. Code-quality + TDD-discipline review of Outside-In TDD implementations. Runs on Haiku for cost efficiency.
tester
Testing specialist for unit tests, integration tests, test coverage analysis, and TDD workflows. Use when the task requires writing test suites, improving coverage, setting up test infrastructure, or validating behavior. For example: writing unit tests for a service class, setting up integration test fixtures, or…