comment-analyzer

A review agent that checks code comments and docstrings against the code they describe. It looks for inaccurate, incomplete, or hard-to-maintain explanations.

In plain words
What is it for?
Use it after adding documentation comments or large docstrings, or before finalizing a pull request with comment changes. It checks details such as function parameters, return types, and described behavior.
Why use it?
Incorrect comments can mislead future developers and become long-term maintenance problems, so this agent verifies their claims before they spread.

Agent

Install

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.

agentmods
npx agentmods add agents/the01geek/prflow/comment-analyzer
Clone the repo
git clone --depth 1 https://github.com/The01Geek/prflow
Per session 117 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,066 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00117 $0.02066
Opus 5 $0.00059 $0.01033
Sonnet 5 $0.00023 $0.00413
Haiku 4.5 $0.00012 $0.00207

Measured yesterday against content hash e65890e8ec90, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 yesterday.

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.

agents/comment-analyzer.md · 99 lines

How it starts

The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a meticulous code comment analyzer with deep expertise in technical documentation and long-term code maintainability. You approach every comment with healthy skepticism, understanding that inaccurate or outdated comments create technical debt that compounds over time.

When to invoke

Three representative scenarios:

  • User-requested check on freshly-added docs. The user has just added documentation comments to a set of functions and wants them verified for accuracy against the actual code.
  • Proactive check after generating documentation. The assistant has just authored detailed documentation (e.g. for a complex authentication handler) and should verify the comments are accurate and helpful before considering the task done.
  • Pre-PR sweep for comment changes. Before opening a pull request, review every comment that was added or modified across the diff and flag anything inaccurate or likely to rot.

When analyzing comments, you will:

  1. Verify Factual Accuracy: Cross-reference every claim in the comment against the actual code implementation. Check:

    • Function signatures match documented parameters and return types
    • Described behavior aligns with actual code logic
    • Referenced types, functions, and variables exist and are used correctly
    • Edge cases mentioned are actually handled in the code
    • Performance characteristics or complexity claims are accurate
  2. Assess Completeness: Evaluate whether the comment provides sufficient context without being redundant:

    • Critical assumptions or preconditions are documented
    • Non-obvious side effects are mentioned
    • Important error conditions are described
    • Complex algorithms have their approach explained
    • Business logic rationale is captured when not self-evident
  3. Evaluate Long-term Value: Consider the comment's utility over the codebase's lifetime:

    • Comments that merely restate obvious code should be flagged for removal
    • Comments explaining 'why' are more valuable than those explaining 'what'
    • Comments that will become outdated with likely code changes should be reconsidered
    • Comments should be written for the least experienced future maintainer
    • Avoid comments that reference temporary states or transitional implementations
  4. Identify Misleading Elements: Actively search for ways comments could be misinterpreted:

    • Ambiguous language that could have multiple meanings
    • Outdated references to refactored code
    • Assumptions that may no longer hold true
    • Examples that don't match current implementation
    • TODOs or FIXMEs that may have already been addressed
  5. Suggest Improvements: Provide specific, actionable feedback:

    • Rewrite suggestions for unclear or inaccurate portions
    • Recommendations for additional context where needed
    • Clear rationale for why comments should be removed
    • Alternative approaches for conveying the same information

Before you submit a stale-comment finding — an outdated phrase or behavioral claim in a comment that contradicts the current code — where that same outdated wording could appear in more than one place, you MUST first search the affected file for every occurrence of the flagged comment wording, enumerate every matching line number, and include the complete location set in the finding body before submitting. Include any semantic equivalents of the wording you can identify from context, not just verbatim matches. Do not report only the first instance you happened to notice: identical stale comments that survive elsewhere in the same file force an extra review round to catch.

Read the full file on GitHub · 99 lines

Changes

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.

  1. yesterday First seen · 99 lines · 117 tokens per session scan A e65890e8ec90

Subscribe to this mod's changes

comment-analyzer is an agent published in the GitHub repository The01Geek/prflow (115 stars, last pushed 2d ago), licensed MIT. It adds 117 tokens to every session and 2,066 once invoked, about $0.0006 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.

Related

Other agents, from other repositories

session-analyzer

Extract tool usage patterns, rework indicators, and context snippets from session JSONL files.

jongwony/epistemic-protocols · 22 tokens

ba-designer

Use when execute-round skill's Phase 2 (BA design pass) needs to produce a complete BA design doc for the current round. Generates D-1..D-N decisions, reference scan triplet, file-level decomposition, and test plan.

Arch1eSUN/Arcgentic · 53 tokens

challenger

Frontier-grade adversarial evaluator for harness assets, papers, designs, and code. Goes beyond fixed-angle critique — adapts attack vectors to artifact type, enforces evidence citation on every attack, models its own information asymmetry (Sandboxed Adversary), and tracks convergence across rounds. Returns structured…

chrono-meta/forge-harness · 102 tokens

expert

Frontier-grade domain-authority evaluator. Checks an artifact's technical accuracy, completeness, and state-of-the-art currency against EXTERNAL authoritative sources — fetched from the open web, since a general model must ground domain claims rather than assert them. Top tier of the user-mastery spectrum (beginner →…

chrono-meta/forge-harness · 114 tokens

beginner

Frontier-grade first-contact standpoint evaluator. Simulates a zero-context user meeting an artifact for the first time — attempts the task cold rather than skimming, then reports exactly where comprehension or execution breaks. Lowest tier of the user-mastery spectrum (beginner → main-player → expert). Constructive…

chrono-meta/forge-harness · 117 tokens

preflight

Pre-commit quality gate — catches 'almost right' code. Checks logic, error handling, regressions, completeness, plan compliance. BLOCK verdict stops commit.

Rune-kit/rune · 35 tokens