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 instructions/webhook-co/webhook/agents-mdgit 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 | $0.02612 | $0.02612 |
| Opus 5 | $0.01306 | $0.01306 |
| Sonnet 5 | $0.00522 | $0.00522 |
| Haiku 4.5 | $0.00261 | $0.00261 |
Grade A, and why
webhook AGENTS.md scanned grade A with 1 finding 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
(command injection in workflow files, unsafe `exec`/`execSync`, `eval`/`new Function`, XSS sinks, How it starts
The opening of the file, as written. The whole thing — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — webhook constitution & governance index
Read this first. The shared, always-read context for every contributor and coding agent in this repository. It is the root "constitution" — the non-negotiables below hold across every surface and package. For a high-level overview, see
README.md. Claude Code reads this same file viaCLAUDE.md.
What this is
Open-core webhook infrastructure: receive, inspect, replay-to-localhost, and reliably deliver webhooks. The wedge is a free, permanent, signed webhook URL with payload inspection and one-command replay-to-localhost. From there it grows into inbound ingestion (verify → dedup → retry → replay) and then outbound delivery. Every capability is reachable identically across CLI, API, web, and MCP. Signing/verification follow the Standard Webhooks spec, for both send and receive.
Non-negotiables (every change must respect these)
These are durable and rarely change. They are not bolt-ons — design for them from day one.
- Compliance-by-design. Encryption in transit and at rest; secrets in a KMS (never in source or plaintext config); an append-only, hash-chained (tamper-evident) audit log; tenant isolation via Postgres row-level security (RLS); region pinning; and PII/PHI scrubbing from logs.
- MCP / AI-native parity. Every capability is reachable from CLI / API / web / MCP identically. A capability added to one surface is considered for all. Ship the MCP server as a first-class surface, including the webhook → agent trigger.
- Private-by-default. Nothing is public, listed, or shared unless explicitly made so.
- Cookieless ingestion on a separate apex. Webhook ingestion and the CLI tunnel live on a
separate registrable apex (
wbhk.my): cookieless, no CORS, path-token routing, and a404for unknown tokens. Never serve ingestion from a primary application subdomain. - Standard-Webhooks-native. Standard Webhooks is the contract for signing and verification, for both send and receive. Do not hand-roll signature schemes.
- Open-core boundary. The open core is Apache-2.0; proprietary code is fenced into
ee/. Open-core code must not depend onee/code; self-host builds simply excludeee/. - Transparent pricing (qualitative). Pricing stays transparent and predictable —
single-dimension (events), disclosed up front (the billable unit — every captured request to an
endpoint — is stated at endpoint creation and on the pricing page), with a soft-cap that pauses
rather than surprises. No surprise billing: predictability comes from disclosure + alerts + pause,
not hidden counters. This shapes engineering: keep event metering accurate and single-dimension;
never build hidden per-step counters. The public pricing ladder (tier names, prices, included
volumes, retention) lives in the repo as one canonical catalog —
@webhook-co/shared/plans— because it is what customers see and what Stripe charges; a drift test keeps every surface agreeing with it. Only the private figures stay out: Stripe price IDs, and the unit-economics / cost research behind the ladder.
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 · 154 lines · 2,612 tokens per session scan A c637c4c3f835
webhook AGENTS.md is an instructions file published in the GitHub repository webhook-co/webhook (0 stars, last pushed 6d ago), licensed Apache-2.0. It adds 2,612 tokens to every session, about $0.0131 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
cloudflare-workers-nextjs-saas-template AGENTS.md
Instructions for LubomirGeorgiev/cloudflare-workers-nextjs-saas-template, covering project context, vinext, general coding rules, control flow and comments.
sonicjs CLAUDE.md
Instructions for SonicJs-Org/sonicjs, covering sonicjs ai development guidelines, core technology stack, workspace boundary (conductor), architecture direction: document model (authoritative) and the 5 document tables (migration 0002documents.sql).
flarestarter CLAUDE.md
Instructions for FlareStarter/flarestarter: This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
baerly-storage CLAUDE.md
Toolchain, verification matrix, module map, conventions, anti-patterns. The main agent entry point.
munkel CLAUDE.md
Instructions for limehq/munkel, covering claude.md, monorepo layout, commands, macos development specifics and deploy.
ai-coding-primer CLAUDE.md
Instructions for ammonhaggerty/ai-coding-primer, covering claude.md, repository structure, guidebook chapters, constraints and writing tone.