A manager for persistent rules that can add prompts or run scripts at selected points during an agent session.

Creating, inspecting, updating, enabling, disabling, deleting, and auditing rules triggered by changed files, commands, or runtime events.

It keeps recurring instructions and automated checks active across sessions, so you do not have to repeat or manually enforce them.

agent-hooks — Skill for Claude Code and Codex by SSBun: A manager for persistent rules that can add prompts…

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/ssbun/csl-agent-kit/agent-hooks

Any agent

npx skills add SSBun/csl-agent-kit --skill agent-hooks

Clone the repo

git clone --depth 1 https://github.com/SSBun/csl-agent-kit

Made for: Claude Code, Codex.

Or install csl, the plugin that ships this one along with the rest of its 33 skills, 2 commands, 5 agents, 10 hooks.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/ssbun/csl-agent-kit/agent-hooks.svg)](https://agentmods.dev/skills/ssbun/csl-agent-kit/agent-hooks)

Your own site

<a href="https://agentmods.dev/skills/ssbun/csl-agent-kit/agent-hooks"><img src="https://agentmods.dev/badge/skills/ssbun/csl-agent-kit/agent-hooks.svg" alt="Measured on agentmods" height="20"></a>

Per session 85 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,044 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.

Model	Per session	Once invoked
Fable 5	$0.00085	$0.01044
Opus 5	$0.00043	$0.00522
Sonnet 5	$0.00017	$0.00209
Haiku 4.5	$0.00009	$0.00104

Measured 3d ago against content hash 103680eda047, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-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 3d ago.

The scan reads SKILL.md. This mod also ships 10 executable files (scripts/agent-hooks.js, scripts/lib/cli.js, scripts/lib/native-hook.js, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/meta/agent-hooks/SKILL.md · 57 lines

How it starts

The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Hooks

Use the bundled CLI as the validation and status authority.

Run node scripts/agent-hooks.js <command> --help before unfamiliar operations. Never hand-edit managed rules or use project RFCs as runtime guidance.

Validate proposed rule files with node scripts/validate-rules.js [--scope global|project] <file.md>... before passing them to update --from. Treat this as frontmatter and V1 rule validation; use show for stored script readiness and effective host status.

Boundaries

Use global hook rules for runtime execution; project hook rules remain metadata-only. Global rules and scripts live under $CSL_AGENT_KIT_HOME/hooks/ (default ~/.csl-agent-kit/hooks/); project rules and scripts live under <workspace>/.agents/hooks/.
Inner scope (inner:*) ships hooks with the agent-hooks skill (e.g. inner:agent-rules and inner:workspace-workflow-gates). Hook source is read-only: do not create, update, or delete it through the CLI. All inner hooks default enabled; enable/disable persists user choices in $CSL_AGENT_KIT_HOME/hooks/config.json (default ~/.csl-agent-kit/hooks/config.json). Optional hookSettings are keyed by qualified inner ID; runtime passes only the matching object to that script as JSON in AGENT_HOOKS_HOOK_CONFIG. inner:agent-rules merges the built-in, user, and project agent-rules.md files in that order; disabling the hook suppresses all three sources.
Codex is the reference host: all events support inject/script (and block where the protocol allows). Claude Code shares Codex's hook protocol and is now supported at parity.
Pi runs triggers inside the csl-context-hooks extension via pi.on(...). Inject works where a handler can rewrite model-facing content (session-start systemPrompt, prompt-submit, after-tool tool_result); script runs as a best-effort side effect on all supported events. A run-script rule with inject-output: true additionally surfaces the script stdout as an injected prompt on inject-capable events. Block and permission/subagent events are not physically realizable on Pi and remain unsupported.
Use Agent Hooks for persistent automation, direct commands for one-time work, and native Git hooks for Git enforcement.

Read the full file on GitHub · 57 lines

Files

What ships with it

18 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

3d ago First seen · 57 lines · 85 tokens per session scan A 103680eda047

Subscribe to this mod's changes

agent-hooks is a skill published in the GitHub repository SSBun/csl-agent-kit (10 stars, last pushed 5d ago), licensed MIT. It adds 85 tokens to every session and 1,044 once invoked, about $0.0004 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.

Building agents

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