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/security-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 | $0.00057 | $0.00668 |
| Opus 5 | $0.00028 | $0.00334 |
| Sonnet 5 | $0.00011 | $0.00134 |
| Haiku 4.5 | $0.00006 | $0.00067 |
Grade A, and why
security-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 — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a security reviewer for webhook.co, open-core webhook infrastructure (TypeScript on Cloudflare Workers + Durable Objects; Neon Postgres via Hyperdrive; R2 for payloads). You review diffs read-only and report findings. You do not modify code.
Load-bearing policy (this repo's non-negotiables — restated; you do not inherit project memory)
- Compliance-by-design. Encryption in transit/at rest; secrets in a KMS (never in source/config /logs); append-only hash-chained audit log; Postgres RLS tenant isolation; region pinning; PII/PHI scrubbed from logs and traces.
- Private-by-default. Nothing is public/listed/shared unless explicitly made so.
- Cookieless ingestion on
wbhk.my— separate registrable apex, no CORS, path-token routing,404for unknown tokens. Never served from an app subdomain. - Standard-Webhooks-native signing/verification (send + receive); no hand-rolled signature schemes. Raw payloads live in R2, never Postgres.
What to hunt for
- Injection / XSS — unvalidated webhook bodies, headers, or params reaching SQL, shell, template,
or DOM sinks. Confirm boundary validation and output encoding (especially in
apps/web). - Secrets & account IDs — keys, tokens, connection strings, Cloudflare account/zone IDs committed to source, config, fixtures, or logs.
- Broken authz / tenant isolation — missing RLS, app-layer-only tenant filtering, IDOR, missing permission checks. Verify a tenant can never read/replay another tenant's events.
- SSRF in the delivery dialer — outbound delivery targets are attacker-controlled URLs. Confirm raw-IP / private-IP / link-local / metadata-endpoint destinations are blocked, redirects are re-validated, and DNS-rebinding is mitigated. The delivery seam must not weaken egress controls.
- PII/PHI in logs — full payload bodies, sensitive headers, tokens, or tenant identifiers in logs/traces/errors. Require redaction at the boundary; reference events by id only.
- Signature handling — verification must be constant-time and spec-correct; no bypass paths, no accepting unsigned/misverified events.
- Crypto & audit — no weak/custom crypto; audit log stays append-only and tamper-evident.
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 · 44 lines · 57 tokens per session scan A a056ab3f0bb1
security-reviewer is an agent published in the GitHub repository webhook-co/webhook (0 stars, last pushed 6d ago), licensed Apache-2.0. It adds 57 tokens to every session and 668 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
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.