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 skills add lfyxhappy/lfcode --skill hook-authoringgit clone --depth 1 https://github.com/lfyxhappy/lfcodeWrote 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.
[](https://agentmods.dev/skills/lfyxhappy/lfcode/hook-authoring)<a href="https://agentmods.dev/skills/lfyxhappy/lfcode/hook-authoring"><img src="https://agentmods.dev/badge/skills/lfyxhappy/lfcode/hook-authoring/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/lfyxhappy/lfcode/hook-authoring"><img src="https://agentmods.dev/badge/skills/lfyxhappy/lfcode/hook-authoring.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 5.1 | $0.00031 | $0.00459 |
| Opus 5.5 | $0.00012 | $0.00184 |
| Sonnet 5.5 | $0.00006 | $0.00092 |
| Haiku 4.5 | $0.00003 | $0.00046 |
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 1mo 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.
What it actually says
Hook Authoring
Use hook_manage for declarative user Hooks. Do not create a plugin when a single command or model judgment attached to an event is sufficient.
Before creating a Hook, state the smallest suitable event, scope, lifetime, matcher, and handler. Run hook_manage list first when changing an existing automation.
- Choose
globalfor an explicit user-wide rule,projectfor one repository, andsessionfor one conversation and its child agents. - Use
temporaryfor one-time or bounded work. Choose exactly one expiry:once,max_runs,current_turn,session_end, orexpires_at. - Use
permanentonly for durable user automation. It always produces a preview and needs user confirmation before create, update, enable, disable, or delete. - A temporary Hook can be created immediately. Never claim it is permanent when its expiry is set.
- Use safe comma-separated globs such as
shell,writeormcp_*; never use regex syntax.
Use a command Handler for deterministic local checks. It receives a redacted JSON event payload on stdin and runs in the event working directory. Keep commands short. Set blockOnNonZero only when a non-zero exit must halt the main operation.
Use a prompt Handler for an isolated allow/block judgment. It has no conversation history and cannot rewrite tool parameters or output. Only explicit block blocks; timeout, unavailable model, and command errors fail open. ask is valid only for PermissionRequest.
Always call hook_manage test with an explicit event sample after creating or editing a Hook. It writes a simulated run record but does not consume once or max_runs lifetime counts. After a real event, call hook_manage get and inspect recentRuns together with lifecycle.remainingRuns; never infer whether a Hook triggered from its definition alone. Use a plugin instead when the feature needs arbitrary code, long-lived background state, custom UI, provider integration, or changes to tool arguments/results.
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.
- 1mo ago First seen · 23 lines · 31 tokens per session scan A ce0a37c49968
hook-authoring is a skill published in the GitHub repository lfyxhappy/lfcode (2 stars, last pushed 26d ago), licensed MIT. It adds 31 tokens to every session and 459 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-05.
Other skills, from other repositories
Review a GitHub PR (via gh)
Review a specific GitHub pull request with gh — fetch the diff, fan out reviewers, consolidate, and optionally post the review. Requires the gh CLI or the GitHub MCP server.
Best of N (parallel attempts)
Delegate N parallel subagents on the same task, then pick the best result.
Design doc (write -> review loop)
Draft a design document and iterate writer/reviewer subagents until consensus.
Implement (multi-agent loop)
Orchestrate an implement -> review -> fix loop with subagents until reviewers sign off.
PR babysit (watch & drive to green)
Watch a pull request and delegate fixes until CI is green and reviews are addressed. Requires the GitHub MCP server or gh.
Review changes (multi-agent)
Delegate read-only reviewers over the local changes/branch and consolidate findings.