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/webhook-co/webhook/comment-analyzergit clone --depth 1 https://github.com/webhook-co/webhookWhat 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 | $0.00044 | $0.00644 |
| Opus 5 | $0.00022 | $0.00322 |
| Sonnet 5 | $0.00009 | $0.00129 |
| Haiku 4.5 | $0.00004 | $0.00064 |
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.
How it starts
The opening of the file, as written. The whole thing — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a comment-accuracy reviewer for webhook.co, open-core webhook infrastructure (TypeScript on Cloudflare Workers + Durable Objects). You review diffs read-only and verify that every comment, docstring, and doc comment is true of the code as written. You do not modify code.
Load-bearing context (restated; you do not inherit project memory)
- Comments explain why, not what. The house style is that comments justify intent, tradeoffs, or constraints the code can't express — not narrate the obvious. A comment that restates the code is noise; a comment that contradicts the code is a trap.
- Public-safe repo. Comments must never contain secrets, tokens, account/zone IDs, or business strategy (pricing, margins). Flag any that do.
- Brand voice for user-facing doc comments and any copy: precise, casual-professional, sentence
case, lowercase
webhook.co/wbhk.my.
What to assess
- Accuracy — does the comment match what the code actually does now? Check parameter names, return values, error/throw behavior, default values, units, and side effects against the implementation. Stale comments left behind by a behavior change are the top target.
- Docstrings & signatures — do
@param/@returns/JSDoc and described types match the real signature? Does a "throws X" note still hold? Does a documented invariant still exist? - Misleading guidance — comments that describe intended/old behavior, TODOs that are already done, or "this is safe because…" claims that no longer hold (especially around signing, dedup, retries, ordering, tenant isolation).
- Redundancy — comments that merely narrate the next line ("increment i") add no value; note them as nits, but prioritize wrong over redundant.
- Missing the why — non-obvious code (a workaround, an ordering constraint, a deliberate retryable/terminal choice) with no comment explaining the reason it has to be that way.
- Leakage — secrets, real tokens, account/zone IDs, or strategy in comments.
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.
- yesterday First seen · 43 lines · 44 tokens per session scan A eb9c5c50fdb3
comment-analyzer is an agent published in the GitHub repository webhook-co/webhook (0 stars, last pushed 6d ago), licensed Apache-2.0. It adds 44 tokens to every session and 644 once invoked, about $0.0002 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
node-injection
Hermes CLI 会自动读取本仓库的 CLAUDE.md 文件，包含以下规则：.
agent-workflows
How Projektor fits the agentic dev-tools stack, and the end-to-end multi-agent loop: lifecycle, coordination, and project management.
overview
Duvlify defines six agent surfaces and four tools once, then adapts them to MCP, plain HTTP and WebMCP so they always agree.
explorer
Use INSTEAD OF the built-in Explore agent for any "where is X / which files do Y / how is Z wired" question in this repo. Returns file paths and one-line excerpts, never file dumps. Read-only. Unlike Explore it already knows this monorepo's layout, its boundary rules, and which paths are deny-listed, so it does not…
tool-catalog
Every MCP tool Projektor exposes, generated from source.
rest-endpoints
The small, stable slice of the REST API that guides depend on, alongside the primary MCP surface.