hookdeck-cli AGENTS.md

Repository instructions for the Hookdeck CLI, a command-line tool for managing webhook infrastructure. Webhooks are automated messages sent between services when something happens.

In plain words
What is it for?
Adding or updating CLI commands, working with API models and validation, handling webhook forwarding, and keeping help text consistent.
Why use it?
They show where commands, API code, configuration, and webhook forwarding live. They also identify the OpenAPI specification as the source of truth for API behaviour.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/hookdeck/hookdeck-cli/agents-md
Clone the repo
git clone --depth 1 https://github.com/hookdeck/hookdeck-cli

Made for: Codex, OpenCode.

Per session 7,487 This file is loaded in full into every session.
When invoked 7,487 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What 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.

ModelPer sessionOnce invoked
Fable 5 $0.07487 $0.07487
Opus 5 $0.03743 $0.03743
Sonnet 5 $0.01497 $0.01497
Haiku 4.5 $0.00749 $0.00749

Measured 2d ago against content hash 11e9d9842014, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

hookdeck-cli AGENTS.md 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 2d ago.

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.

AGENTS.md · 594 lines

How it starts

The opening of the file, as written. The whole thing — 594 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS Guidelines for Hookdeck CLI

This repository contains the Hookdeck CLI, a Go-based command-line tool for managing webhook infrastructure. When working with this codebase, please follow these guidelines to maintain consistency and ensure proper functionality.

1. Project Structure & Navigation

Core Directories

  • pkg/cmd/ - All CLI commands (Cobra-based)
  • pkg/hookdeck/ - API client and models
  • pkg/config/ - Configuration management
  • pkg/listen/ - Local webhook forwarding functionality
  • main.go - Main entry point (repo root)
  • REFERENCE.md - Complete CLI documentation and examples

Key Files

  • https://api.hookdeck.com/2025-07-01/openapi - API specification (source of truth for all API interactions)
  • pkg/cmd/sources/ - Fetches and caches the OpenAPI spec for source type enum and auth rules; use for validation and help in source and connection management
  • pkg/cmd/helptext.go - Shared Short/Long help for resource commands (sources, connections); use when adding or editing command help to avoid duplication
  • .plans/ - Implementation plans and architectural decisions
  • AGENTS.md - This file (guidelines for AI agents)

2. OpenAPI to CLI Conversion Standards

When adding new CLI commands that interact with the Hookdeck API, follow these conversion patterns:

Parameter Mapping Rules

# Nested JSON objects → Flat CLI flags
API: { "configs": { "strategy": "final_attempt" } }
CLI: --strategy final_attempt

# Arrays → Comma-separated values
API: { "connections": ["conn_1", "conn_2"] }
CLI: --connections "conn_1,conn_2"

# Boolean presence → Presence flags
API: { "channels": { "email": {} } }
CLI: --email

# Complex objects with values → Value flags
API: { "channels": { "slack": { "channel_name": "#alerts" } } }
CLI: --slack-channel "#alerts"

Flag Naming Conventions

  • Resource identifiers: Always --name for human-readable names
  • Type parameters:
    • Individual resource commands: Use --type (clear context)
      • Sources: hookdeck source create --type STRIPE
      • Destinations: hookdeck destination create --type HTTP
      • Issue Triggers: hookdeck issue-trigger create --type delivery
    • Connection creation: Use prefixed flags to avoid ambiguity when creating inline resources
      • --source-type STRIPE when creating source inline
      • --destination-type HTTP when creating destination inline
      • This prevents confusion between source and destination types in single command
  • Authentication: Standard patterns (--api-key, --webhook-secret, --basic-auth)
    • Connection creation: Use prefixed authentication to avoid collisions
      • --source-webhook-secret for source authentication
      • --destination-api-key for destination authentication
  • Collections: Use comma-separated values (--connections "a,b,c")
  • Booleans: Use presence flags (--email, --pagerduty, --force)

Read the full file on GitHub · 594 lines

Changes

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.

  1. 2d ago First seen · 594 lines · 7,487 tokens per session scan A 11e9d9842014

Subscribe to this mod's changes

hookdeck-cli AGENTS.md is an instructions file published in the GitHub repository hookdeck/hookdeck-cli (360 stars, last pushed 8d ago), licensed Apache-2.0. It adds 7,487 tokens to every session, about $0.0374 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 2026-08-30.