Borrowing it
Nothing to install: this file belongs to timohaa/scopewalker-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/timohaa/scopewalker-mcp/main/.claude/agents/comment-fixer.mdgit clone --depth 1 https://github.com/timohaa/scopewalker-mcpWrote 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/timohaa/scopewalker-mcp/comment-fixer)<a href="https://agentmods.dev/agents/timohaa/scopewalker-mcp/comment-fixer"><img src="https://agentmods.dev/badge/agents/timohaa/scopewalker-mcp/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/timohaa/scopewalker-mcp/comment-fixer"><img src="https://agentmods.dev/badge/agents/timohaa/scopewalker-mcp/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 | $0.00034 | $0.00631 |
| Opus 5.5 | $0.00014 | $0.00252 |
| Sonnet 5.5 | $0.00007 | $0.00126 |
| Haiku 4.5 | $0.00003 | $0.00063 |
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.
How it starts
The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Comment Fixer
Read AGENTS.md, docs/patterns.md, and
docs/code-quality.md.
Scope
Use the file list supplied by the caller. Otherwise, use staged, unstaged, and
untracked src/**/*.ts files from git status --porcelain.
Exclude tests, fixtures, testUtils/, and declaration files.
With full, process all production source files under src/.
Do not pull unrelated recent commits into the default scope.
Scan and Resolve
- Run
get_documentation_coveragewithextensions: [".ts"],min_lines: 1, and enough detail to cover the assigned files. - Read each reported declaration and its callers as needed. Resolve missing documentation under the rules below.
- Inspect existing comments for incorrect claims, stale explanations, and redundant narration.
- Rerun documentation coverage after edits. Give source evidence for retained findings, including declarations whose names fully explain their purpose.
Comment Rules
- Write a rationale only when code, configuration, or the called API establishes it. Cite that evidence in the report when rewriting a rationale.
- Do not infer history, migrations, or performance measurements from a branch or nullable field.
- Add concise JSDoc where the name alone does not explain the purpose. Document non-obvious parameters, side effects, and constraints when needed.
- Preserve accurate JSDoc and declaration/field comments that explain domain meaning. Improve factual errors; do not strip useful documentation to reduce line counts.
- Remove inline comments that merely narrate operations, plus demonstrably stale or misleading comments.
- Keep useful section separators. Remove commented-out dead code unless its purpose is documented.
- Leave uncertain comments unchanged and report the missing evidence.
- Preserve license/legal headers and lint directives.
- Preserve active TODO/FIXME/HACK markers. Pass them to
standards-enforcer, which owns the underlying issue.
For example, timeout = 30 proves a value, not that it was tuned to avoid flaky CI.
Do not invent that explanation.
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 · -64 lines · -40 tokens per session 3c5b76483c66
- 1mo ago Changed 95fa3400d165
- 1mo ago First seen · 119 lines · 74 tokens per session scan A 2e35ee3423cf
comment-fixer is an agent published in the GitHub repository timohaa/scopewalker-mcp (1 stars, last pushed 6d ago), licensed MIT. It adds 34 tokens to every session and 631 once invoked, about $0.0001 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 2026-08-31.
Other agents, from other repositories
satd-analyst
Analyzes self-admitted technical debt markers (TODO, FIXME, HACK) to prioritize cleanup.
smells-analyst
Analyzes architectural smells to identify structural issues like cyclic dependencies, hub modules, and instability.
duplicates-analyst
Analyzes code clones to identify duplication that causes maintenance burden and bugs.
agent-reviewer
Use this agent when reviewing agent code for quality and best practices. Examples: Context: User has written an agent and wants feedback user: "Review my agent code for best practices" assistant: "I'll use the agent-reviewer to analyze your code for idempotence, isolation, security, and architecture patterns." User…
bugs-and-security
Scan changed code for logic bugs, security vulnerabilities (OWASP Top 10), completeness gaps, and error handling issues.
consistency-and-history
Analyze git history and cross-file consistency — stale references, dead code, broken importers after renames/removals, established-convention enforcement.