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/rjmurillo/ai-agents/comment-analyzergit clone --depth 1 https://github.com/rjmurillo/ai-agentsWhat 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 | $0.00060 | $0.01409 |
| Opus 5 | $0.00030 | $0.00705 |
| Sonnet 5 | $0.00012 | $0.00282 |
| Haiku 4.5 | $0.00006 | $0.00141 |
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 3d 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 — 112 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 (Outdated parameter names, wrong return semantics, stale TODOs, references to removed functions.)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.
- 3d 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 (45 stars, last pushed 3d ago), licensed MIT. It adds 60 tokens to every session and 1,409 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 2026-08-30.
Other agents, from other repositories
config-safety-reviewer
Configuration safety specialist focusing on production reliability, magic numbers, pool sizes, timeouts, and connection limits. Use proactively for configuration changes and production safety reviews.
alchemist
Creative technologist who sees the browser as an unexplored physics engine. Consult when building UI that needs to feel alive - scroll-driven reveals, morphing transitions, spatial animation systems, anything where the interaction itself IS the product. Thinks in weight, tension, and breath before thinking in code.…
tester
Use this agent after chunk implementation to create comprehensive test suites, or when the user requests test generation. Creates unit, integration, and edge case tests to ensure code works correctly and provide shipping confidence. Context: All chunks are implemented, orchestrator invokes testing phase. user: "All…
claims-auditor
Use this agent once per story at story-final, after validation passes, to verify the orchestrator's completion claims against on-disk artifacts before the story is marked complete. Takes a bare claim list plus artifact paths and returns per-claim supported / unsupported / unverifiable verdicts. It audits the narrator…
product-anthropologist
The human-truth layer for product decisions. Consult when diagnosing why users aren't adopting, when deciding whether to iterate or kill, when interpreting user feedback or metrics, when designing research for AI-powered products, when a founder's conviction is outrunning evidence, or any moment where the question is…
muse
The creative product mind that knows why some features become part of someone's identity and others get used once. Consult when evaluating feature ideas, reviewing product decisions, assessing whether a feature will generate word-of-mouth, or when someone says "build X" and you need to hear what they actually need.…