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 BbgnsurfTech/claude-skills-collection --skill hook-factorygit clone --depth 1 https://github.com/BbgnsurfTech/claude-skills-collectionWrote 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/bbgnsurftech/claude-skills-collection/hook-factory)<a href="https://agentmods.dev/skills/bbgnsurftech/claude-skills-collection/hook-factory"><img src="https://agentmods.dev/badge/skills/bbgnsurftech/claude-skills-collection/hook-factory/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/bbgnsurftech/claude-skills-collection/hook-factory"><img src="https://agentmods.dev/badge/skills/bbgnsurftech/claude-skills-collection/hook-factory.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 | $0.00036 | $0.02988 |
| Opus 5 | $0.00018 | $0.01494 |
| Sonnet 5 | $0.00007 | $0.00598 |
| Haiku 4.5 | $0.00004 | $0.00299 |
Grade D, and why
hook-factory scanned grade D with 2 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 7d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
# Install to user level (~/.claude/settings.json) Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- **Safety**: No destructive operations (rm -rf, etc.) The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What ships with it
27 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.
- examples/auto-format-python/hook.json 542 B
- examples/auto-format-python/README.md 2.7 KB
- examples/desktop-notify/hook.json 649 B
- examples/desktop-notify/README.md 4.2 KB
- examples/git-auto-add/hook.json 584 B
- examples/git-auto-add/README.md 2.5 KB
- examples/load-context/hook.json 455 B
- examples/load-context/README.md 2.5 KB
- examples/pre-push-check/hook.json 1.6 KB
- examples/pre-push-check/README.md 4.0 KB
- examples/pre-tool-validation/hook.json 865 B
- examples/pre-tool-validation/README.md 3.1 KB
- examples/prompt-preprocessor/hook.json 757 B
- examples/prompt-preprocessor/README.md 3.0 KB
- examples/security-scan/hook.json 2.1 KB
- examples/security-scan/README.md 5.7 KB
- examples/session-cleanup/hook.json 777 B
- examples/session-cleanup/README.md 3.7 KB
- examples/test-runner/hook.json 432 B
- examples/test-runner/README.md 2.5 KB
- generator.py 17 KB runs code
- hook_factory.py 23 KB runs code
- install-hook.sh 4.6 KB runs code
- installer.py 18 KB runs code
- README.md 14 KB
- templates.json 23 KB
- validator.py 31 KB runs code
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.
- 7d ago First seen · 462 lines · 36 tokens per session scan D 3d5ef9bd670e
hook-factory is a skill published in the GitHub repository BbgnsurfTech/claude-skills-collection (21 stars, last pushed 8mo ago), with no licence file. It adds 36 tokens to every session and 2,988 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it D with 2 findings (reads agent configuration directories, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
hook-factory
Generate production-ready Claude Code hooks with interactive Q&A, automated installation, and enhanced validation. Supports 10 templates across 7 event types for comprehensive workflow automation.
intent-recognition
Classifies automation requests using two decisions: anchor (which primitive owns the top-level control flow — workflow-anchored, agent-anchored, needs-clarification, or out-of-scope) and embedsother (whether the other primitive appears embedded inside — an agent step inside a workflow, or a workflow invoked as an…
post-build-flow
Handles workflow verification and setup after build-workflow succeeds, or when the message contains workflow-verification-follow-up or workflow-setup-required. Load after direct builds, when verificationReadiness requires action, or on orchestrator verify/setup follow-up turns.
planned-task-runtime
Handles system follow-up turns: planned-task-follow-up (synthesize, replan, build-workflow, checkpoint), background-task-completed, running-tasks context, and create-tasks silence rules. Load whenever any of these tags appear or after calling create-tasks.
config-evals
Builds and maintains configuration-based evaluations on a workflow with the eval-config tool. Use when the user asks to set up, add, view, change, or remove an evaluation, score, grade, or judge a workflow's output, or measure answer quality against a test dataset. This is the only eval form Instance AI handles — it…
one-off-operations
Handles one-off operations: the request is a concrete effect that happens once — export or copy data somewhere, a migration, a backfill, a cleanup — with no trigger, schedule, or reuse intent. The workflow is the vehicle, not the deliverable. Users rarely say "one-off"; infer it from the task's shape. Load before…