hooks

A command for managing event-based actions, called hooks, in `.ai/hooks.toml`. It can list existing hooks, add one, or show how hooks will be converted for different coding tools.

In plain words
What is it for?
Use it to audit hooks, define actions that run around tool calls, and preview their format for each supported tool.
Why use it?
It keeps hook settings in one place and helps you check which tools support them before syncing. This avoids editing separate tool-specific files by hand.

Command

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 commands/thethoughtagen/agentsync/hooks
Clone the repo
git clone --depth 1 https://github.com/TheThoughtagen/agentsync
Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 279 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 $0.00015 $0.00279
Opus 5 $0.00008 $0.00139
Sonnet 5 $0.00003 $0.00056
Haiku 4.5 $0.00002 $0.00028

Measured yesterday against content hash b074238f1ed7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

hooks 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.

plugins/aisync/commands/hooks.md · 36 lines

What it actually says

/aisync:hooks

Manage hook definitions in .ai/hooks.toml. Accepts a subcommand argument: list, add, or translate.

Usage

List hooks

aisync hooks list

Run this to display all defined hooks. Present the output showing each hook's event, matcher, command, and per-tool support info (which tools support each hook natively).

Add a hook

aisync hooks add <event> --matcher <matcher> --command <command> [--timeout <seconds>]

Run with the user's specified parameters to add a new hook definition to .ai/hooks.toml.

Translate hooks

aisync hooks translate

Run this to preview how canonical hooks translate to each tool's native format. Show the translated output grouped by tool so the user can see exactly what each tool will receive.

Notes

  • Hook definitions live in .ai/hooks.toml — always edit there, not in tool-native files.
  • Use list to audit current hooks and check tool compatibility.
  • Use translate to verify cross-tool behavior before syncing.
  • After adding or modifying hooks, run /aisync:sync to propagate changes.
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. yesterday First seen · 36 lines · 15 tokens per session scan A b074238f1ed7

Subscribe to this mod's changes

hooks is a command published in the GitHub repository TheThoughtagen/agentsync (2 stars, last pushed 5mo ago), licensed MIT. It adds 15 tokens to every session and 279 once invoked, about $0.0001 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.