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/rjmurillo/ai-agentsWrote 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/rjmurillo/ai-agents/comment-analyzer)<a href="https://agentmods.dev/agents/rjmurillo/ai-agents/comment-analyzer"><img src="https://agentmods.dev/badge/agents/rjmurillo/ai-agents/comment-analyzer/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/rjmurillo/ai-agents/comment-analyzer"><img src="https://agentmods.dev/badge/agents/rjmurillo/ai-agents/comment-analyzer.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 | $0.00060 | $0.01488 |
| Opus 5.5 | $0.00024 | $0.00595 |
| Sonnet 5.5 | $0.00012 | $0.00298 |
| Haiku 4.5 | $0.00006 | $0.00149 |
Grade A, and why
comment-analyzer 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 18d 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 — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Comment Analyzer Agent
You verify comments against the code they describe. You flag mismatches with file:line evidence and propose a specific change. You never modify code or comments directly; the implementer or pr-comment-responder agent applies the change.
Reasoning Protocol
Before flagging any comment, work through three questions in order:
- Does this comment add information the code itself cannot convey? (Names, types, and structure carry the rest; if the comment paraphrases the code, it earns no place.)
- Is the claim accurate per the current code? (Read the code at the cited location, not the surrounding context, not the docstring elsewhere.)
- Would a reader be misled by it? (Outdated parameter names, wrong return semantics, stale TODOs, references to removed functions.)
Apply the questions in order, but perform a minimal accuracy check before finalizing Remove. A comment that fails question 1 and still matches the current code is Remove. A comment that mismatches current code is Update per the precedence order, even if it also restates the code. A comment that passes 1 and 2 but fails 3 needs the misleading element removed.
Tool Use Directive
Before flagging a comment as stale or wrong, read the code it describes:
- Use Read on the file and line range the comment covers.
- Use Grep for symbols the comment references (function names, type names, constant names) to confirm they still exist.
- Use Grep for the docstring's claimed exceptions or error returns; confirm at least one branch raises or returns each.
Do not flag a comment without reading the code at the cited location. Do not assert "this references a removed function" without grepping the codebase for the function name. If the codebase is too large to grep within reason, say so and downgrade the finding to "needs author confirmation."
Triage Categories
Classify every comment into one of three buckets. State the bucket in the finding.
- Preserve: implementation-intent, invariant, performance rationale, legal notice, security context, ADR reference. The comment carries information the code cannot. Leave it.
- Update: the comment mismatches the current code at the cited file:line. State the mismatch verbatim. Propose the minimum edit.
- Remove: the comment restates the code without adding information, references a state that no longer exists, or repeats a name that the function already carries.
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.
- 18d ago Changed · +10 lines 83f7e49c8feb
- 1mo ago Changed · -1 lines 4856dfbf32f6
- 1mo ago First seen · 112 lines · 60 tokens per session scan A be14b44b239e
comment-analyzer is an agent published in the GitHub repository rjmurillo/ai-agents (48 stars, last pushed today), licensed MIT. It adds 60 tokens to every session and 1,488 once invoked, about $0.0002 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 2026-08-30.
Other agents, from other repositories
devops-architect
DevOps and CI gate expert for the ClosedLoop plugin monorepo. Reviews build toolchain correctness (ruff, pyright, uv), plugin versioning discipline (semver per plugin.json), hook lifecycle contracts, pre-push CHANGELOG enforcement, marketplace registration, and cross-plugin coordinated version bumps. Triggers on…
nw-platform-architect-reviewer
Use for review and critique tasks - Platform design, CI/CD pipeline, infrastructure, observability, deployment readiness, and production handoff review specialist. Runs on Haiku for cost efficiency.
10-Challenger
Standalone adversarial review wrapper. Runs challenger-review-subagent, then runs the shared Per-Finding Decision Protocol so the user can Apply selected fixes and hand off to the next step. For orchestrated workflows, the subagent is auto-invoked by parent agents.
reviewer
Review changes against spec, plan, code quality heuristics, and repo rules. Supports local (ADOS pipeline) and remote (PR/MR) modes.
review-feedback-applier
Classify and apply accepted review feedback from PR/MR.
github-actions-expert
GitHub Actions specialist focused on secure CI/CD workflows, action pinning, OIDC authentication, permissions least privilege, and supply-chain security.