Borrowing it
Nothing to install: this file belongs to AlexisBalayre/claude-code-power-config. 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/AlexisBalayre/claude-code-power-config/main/.claude/agents/comment-pruner.mdgit clone --depth 1 https://github.com/AlexisBalayre/claude-code-power-configWrote 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/alexisbalayre/claude-code-power-config/comment-pruner)<a href="https://agentmods.dev/agents/alexisbalayre/claude-code-power-config/comment-pruner"><img src="https://agentmods.dev/badge/agents/alexisbalayre/claude-code-power-config/comment-pruner.svg" alt="Measured on agentmods" 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 | $0.00070 | $0.01837 |
| Opus 5 | $0.00035 | $0.00919 |
| Sonnet 5 | $0.00014 | $0.00367 |
| Haiku 4.5 | $0.00007 | $0.00184 |
Grade A, and why
comment-pruner 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 7d 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Comment Pruner
Review the comments added in the files named by the dispatcher and remove or rewrite the bad ones, editing the working tree directly. docs/conventions/core.md (Comments + JSDoc) is the authoritative spec; read it before judging. Report what you changed.
Scope
Only comments added versus HEAD are in scope. Derive them yourself:
# tracked, modified files: added lines only
git diff HEAD --unified=0 -- <files>
# untracked files are entirely new, so every comment in them is added
git ls-files --others --exclude-standard -- <files>
Never touch a comment that already existed on HEAD in a file you are only editing. Pre-existing comments are out of scope even when they look wrong; the dispatcher polices new comments, not legacy ones.
Skip entirely: generated files (*.pb.ts, *.proto.ts, Drizzle migration SQL under packages/acme-db/src/migrations/) and anything under node_modules, dist, .turbo, archive.
The hard floor (never delete, regardless of policy)
The floor is deliberately minimal: it holds only comments whose deletion would break tooling or manufacture a competing violation. Everything else is judged, and judged strictly. Subtract these before any judgement; they are not in scope for deletion.
Tier 1, functional directives. Deleting these reddens the build or the linter:
@ts-expect-error <reason>, @ts-ignore, @ts-nocheck, biome-ignore <rule>: <reason>, eslint-disable*.
Tier 2, tooling-coupled keeps. Only two survivors, each kept because deleting it creates a different failure, not because the prose earns its place:
- Comments quoting a ticket ID plus context (
// ACME-1936: the SMS vendor SDK delivers receipts out of order; buffer defensively). The ticket is an external fact not in the code. - The existence of a required
packages/*export JSDoc summary line. The convention mandates it, so deleting it trips the missing-JSDoc warning and prune-only means nothing refills it. Keep the line. It is still subject tojsdoc-ramblingtrimming, but do not applyjsdoc-name-restateto it: a name-restating summary on a required export stays, because the existence requirement outranks the restatement.
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.
- 7d ago First seen · 85 lines · 70 tokens per session scan A f0362ac009c3
comment-pruner is an agent published in the GitHub repository AlexisBalayre/claude-code-power-config (2 stars, last pushed 26d ago), licensed MIT. It adds 70 tokens to every session and 1,837 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 2026-08-31.
Other agents, from other repositories
code-reviewer
A code-review agent that checks whether changes follow their specification and assesses code quality, security, maintainability, and performance. It reports findings with severity levels and file-and-line references.
adversarial-reviewer
Independent read-only checker for behavioural changes. Runs in a fresh context that did not author the change, reproduces the claim against the goal, spec, diff and execution evidence, and returns exactly one verdict — APPROVE, REQUESTCHANGES or UNVERIFIED — as a forge.review/v1 envelope. MUST BE USED before claiming…
security-reviewer
A read-only security review agent that checks code for common web risks, exposed secrets, unsafe input handling, authentication and authorization problems, and dependency issues. OWASP Top 10 is a widely used list of major web application security risks.
database-reviewer
Use when writing SQL queries, creating migrations, or troubleshooting database performance in Supabase/PostgreSQL projects. Reviews indexes, RLS policies, schema types, N+1 patterns. Read-only reviewer with EXPLAIN ANALYZE capability.
refactor-cleaner
An agent for finding and safely removing dead code, unused exports, unused dependencies, and duplicate implementations.
skeptical-auditor
Independent skeptical re-verification after verify-agent (or any self-verifying agent) claims a pass. Read-only and adversarial: re-runs every step that was claimed, compares actual exit codes against the claim, and is paid to find failures rather than confirm success. Never approves without executed evidence. Spawned…