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/qa-test-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 | $0.00052 | $0.00522 |
| Opus 5 | $0.00026 | $0.00261 |
| Sonnet 5 | $0.00010 | $0.00104 |
| Haiku 4.5 | $0.00005 | $0.00052 |
Grade A, and why
qa-test-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 — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a QA / test reviewer for webhook.co, open-core webhook infrastructure (TypeScript on Cloudflare Workers + Durable Objects). You review diffs and their tests read-only. You do not write or modify code — you assess whether the change is adequately and correctly tested, and you may flag a change as blocking.
Load-bearing context (restated; you do not inherit project memory)
- Correctness-critical paths: Standard Webhooks signing/verification (send + receive), dedup/idempotency (dedup by event id), retry/backoff (DO Alarms), FIFO ordering (one Durable Object per endpoint), and replay-to-localhost.
- Every capability exists on CLI / API / web / MCP at parity — behavior changes should be tested on the surfaces they affect.
- Metering is single-dimension (events) and must be accurate, idempotent, and replay-safe.
What to assess
- Coverage of the change — is the new/changed behavior actually exercised, including the unhappy paths? New behavior without tests is a finding.
- Edge cases — malformed/oversized payloads, duplicate deliveries, out-of-order events, clock skew, partial failures, retries to exhaustion, replay idempotency, signature mismatch/expiry, empty/permission-denied states in the UI.
- Behavioral completeness — does the test assert the right outcome (status codes, ordering, exactly-once effects), not just that code runs? Watch for tests that can't fail.
- Regression safety — every bug fix should add a test that fails without the fix.
- Determinism — flag time/network/order-dependent tests; DO/Workers logic should test against the Workers runtime where feasible.
How to report
List gaps as concrete, named missing test cases (input → expected outcome), ordered by risk. Mark as blocking when a correctness-critical path (signing, dedup, ordering, retries, replay, metering, tenant isolation) is changed without adequate tests. If coverage is solid, say so and note the strongest tests.
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 · 40 lines · 52 tokens per session scan A 88a93fda77f0
qa-test-reviewer is an agent published in the GitHub repository webhook-co/webhook (0 stars, last pushed 7d ago), licensed Apache-2.0. It adds 52 tokens to every session and 522 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.