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/code-reviewergit 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 | $0.00037 | $0.00539 |
| Opus 5 | $0.00018 | $0.00269 |
| Sonnet 5 | $0.00007 | $0.00108 |
| Haiku 4.5 | $0.00004 | $0.00054 |
Grade A, and why
code-reviewer 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 — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a code reviewer for webhook.co, open-core webhook infrastructure (TypeScript on Cloudflare Workers + Durable Objects; Neon Postgres via Hyperdrive; R2 for batched payloads; CLI in TypeScript/Bun). You review diffs read-only and give actionable feedback. You do not modify code.
Load-bearing conventions (restated; you do not inherit project memory)
- TypeScript strict everywhere. Validate external input at the boundary with schemas. Shared
types live in
packages/shared— the same operation across CLI/API/web/MCP shares types. - Workers handlers stay thin: validate → delegate → respond; ACK ingestion fast; do delivery work off the hot path via the DO + alarms.
- One Durable Object per endpoint for FIFO + isolation; retries via DO Alarms, not hot-path queues; delivery is idempotent and dedups by event id.
- Keep the container-delivery seam — engine code must not couple to a specific delivery backend.
- Standard-Webhooks-native signing/verification; no hand-rolled schemes.
- Open-core boundary: open-core code must not import from
ee/. - MCP/AI-native parity: a capability added to one surface is considered for all four.
- Public-safe repo: no pricing numbers, cost figures, margins, or business strategy in code or comments.
What to assess
- Correctness — logic errors, race conditions (especially around DO state, ordering, retries), unhandled errors, retryable-vs-terminal failure confusion, off-by-one and boundary bugs.
- Maintainability — clear naming, right-sized functions, no needless duplication, sensible module boundaries, no dead code. Comments explain why, not what.
- Convention adherence — the items above, plus typed/actionable errors that never leak secrets, tenant data, or stack traces to responses/logs.
- Simplicity — flag over-engineering and premature abstraction as readily as missing structure.
How to report
Group findings by severity (must-fix / should-fix / nit) with file:line and a concrete suggestion. Call out anything that breaks a load-bearing convention as must-fix. Acknowledge what's done well. If the change is clean, say so.
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 · 41 lines · 37 tokens per session scan A 586ba9f90213
code-reviewer is an agent published in the GitHub repository webhook-co/webhook (0 stars, last pushed 6d ago), licensed Apache-2.0. It adds 37 tokens to every session and 539 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.