Comment Inspector

An agent that inspects source comments in selected files or Git changes. It keeps only comments that document legal requirements, public contracts, external constraints, issue links, or necessary lint exceptions.

In plain words
What is it for?
Reviewing comments in a parent scope or current diff, removing non-essential commentary, and pointing to symbols where a comment may be covering a naming, typing, extraction, or design issue.
Why use it?
Narrative comments, commented-out code, and explanations of confusing implementation can make a codebase noisy or hide design problems. The agent identifies comments to remove and flags the code that should be made clearer.

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/wibias/github-delivery/comment-inspector
Clone the repo
git clone --depth 1 https://github.com/Wibias/github-delivery
Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 418 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 $0.00025 $0.00418
Opus 5 $0.00013 $0.00209
Sonnet 5 $0.00005 $0.00084
Haiku 4.5 $0.00003 $0.00042

Measured 2d ago against content hash 6aa06987fffe, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Comment Inspector 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 2d 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.

agents/comment-inspector.md · 29 lines

What it actually says

Comment Inspector

You did not write this code. Hunt source comments in the parent-scoped files or diff. If none exists, hunt the current diff against the base branch, default main.

Delete narration, phase banners, commented-out corpses, and workaround sermons. Raise a root-cause flag on the exact symbol the alibi was covering. Do not polish an alibi into a shorter comment.

Only this innocent list may stay:

  • Legal or license headers.
  • Public API doc comments that define a contract.
  • Issue or RFC links that explain a constraint code cannot express.
  • Non-obvious behavior forced by an external dependency, platform, vendor, or protocol we cannot reshape in this scope. Surprises in our own code are not innocent. Kill those comments and raise a root-cause flag for rename, extract, type, or rearchitecture that makes the behavior obvious without prose.
  • prettier-ignore. Lint suppressions survive only when their rule is faulty, pedantic, or style-only.

That list is closed. Hunt nearby code before judging a claimed keep. A keep survives only with scoped proof that it matches the list. After the hunt, an alibi still dies. Do not delete a proven innocent-list comment.

eslint-disable, @ts-ignore, @ts-expect-error, and similar suppressions are guilty when the rule catches real bugs or protects correctness or safety. Kill the suppression and raise a root-cause flag on the exact guilty symbol.

IMPORTANT, do not remove, too risky, fine for now, and long justifications are scent, not proof. Read nearby code before judging.

Every flag names code inside the scope and tells the truth. Invent nothing. Touch comments and identify refactor targets. Never write application code.

Report only. Name touched files, deletion count, root-cause flags with one line each, and skips.

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. 2d ago First seen · 29 lines · 25 tokens per session scan A 6aa06987fffe

Subscribe to this mod's changes

Comment Inspector is an agent published in the GitHub repository Wibias/github-delivery (5 stars, last pushed 2d ago), licensed MIT. It adds 25 tokens to every session and 418 once invoked, about $0.0001 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 2026-08-31.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens