hook-authoring

Instructions for writing hook definitions in `.ai/hooks.toml`, a TOML configuration file. Hooks are actions that run before or after an AI tool is used, when a session changes, or at other supported events.

In plain words
What is it for?
Use it when creating or editing hook files, choosing events and matchers, and checking how one hook definition maps to different AI tools.
Why use it?
It explains the allowed event names and matching rules, including which events work across Claude Code and Cursor. This reduces mistakes when creating hooks that must be translated between tools.

Skill for Claude CodeCodex

Part of the aisync plugin — 2 skills, 7 commands, 2 hooks shipped together

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 skills/thethoughtagen/agentsync/hook-authoring
Any agent
npx skills add TheThoughtagen/agentsync --skill hook-authoring
Clone the repo
git clone --depth 1 https://github.com/TheThoughtagen/agentsync

Made for: Claude Code, Codex.

Or install aisync, the plugin that ships this one along with the rest of its 2 skills, 7 commands, 2 hooks.

Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,137 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00035 $0.01137
Opus 5 $0.00017 $0.00568
Sonnet 5 $0.00007 $0.00227
Haiku 4.5 $0.00003 $0.00114

Measured 2d ago against content hash 9e2c9d74a17a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

hook-authoring 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.

plugins/aisync/skills/hook-authoring/SKILL.md · 137 lines

How it starts

The opening of the file, as written. The whole thing — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Hook Authoring Guide

File Format

Hooks are defined in .ai/hooks.toml using TOML. Each hook is grouped under an [[EventName]] section with an optional matcher field, and contains one or more [[EventName.hooks]] entries.

[[PreToolUse]]
matcher = "Bash"

[[PreToolUse.hooks]]
type = "command"
command = "bash .ai/scripts/validate-bash.sh"
timeout = 10

Valid Events

Shared Events (work in both Claude Code and Cursor via aisync translation)

Event Description
PreToolUse Fires before a tool is invoked. Use matcher to target specific tools.
PostToolUse Fires after a tool completes. Use matcher to target specific tools.
Stop Fires when the agent stops (completes a response).
SubagentStop Fires when a sub-agent stops.

Claude Code Only (via aisync translation)

Event Description
Notification Fires when a notification is sent.

Cursor Only (via aisync translation)

Event Description
PostToolUseFailure Fires when a tool invocation fails.
SessionStart Fires when a new session begins.
SessionEnd Fires when a session ends.
BeforeShellExecution Fires before a shell command runs.
AfterShellExecution Fires after a shell command completes.
BeforeReadFile Fires before reading a file.
AfterFileEdit Fires after a file is edited.
BeforeSubmitPrompt Fires before a prompt is submitted.
PreCompact Fires before context compaction.
AfterAgentResponse Fires after the agent responds.
AfterAgentThought Fires after an agent thought step.
SubagentStart Fires when a sub-agent starts.
BeforeMCPExecution Fires before an MCP tool call.
AfterMCPExecution Fires after an MCP tool call completes.

Note: Claude Code natively supports additional events (SessionStart, SessionEnd, UserPromptSubmit, PreCompact) that aisync does not yet translate. When writing hooks for these events in .ai/hooks.toml, aisync will currently skip them during Claude Code translation. To use these events, configure them directly in .claude/settings.json or via a Claude Code plugin's hooks.json.

Read the full file on GitHub · 137 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 · 137 lines · 35 tokens per session scan A 9e2c9d74a17a

Subscribe to this mod's changes

hook-authoring is a skill published in the GitHub repository TheThoughtagen/agentsync (2 stars, last pushed 5mo ago), licensed MIT. It adds 35 tokens to every session and 1,137 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens