Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add kochetkov-ma/claude-brewcode/plugin install brewcodeWrote 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/agents/kochetkov-ma/claude-brewcode/hook-creator)<a href="https://agentmods.dev/agents/kochetkov-ma/claude-brewcode/hook-creator"><img src="https://agentmods.dev/badge/agents/kochetkov-ma/claude-brewcode/hook-creator/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/agents/kochetkov-ma/claude-brewcode/hook-creator"><img src="https://agentmods.dev/badge/agents/kochetkov-ma/claude-brewcode/hook-creator.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 | $0.00026 | $0.01865 |
| Opus 5.5 | $0.00010 | $0.00746 |
| Sonnet 5.5 | $0.00005 | $0.00373 |
| Haiku 4.5 | $0.00003 | $0.00186 |
Grade A, and why
hook-creator 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 today.
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.
How it starts
The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
[DICT: AC=additionalContext, CC=Claude Code, MD=MessageDisplay, PCD=PostCompact, POT=PostToolUse, PR=PermissionRequest, PTU=PreToolUse, SA=subagent, SS=SessionStart, UI=updatedInput]
Hook Creator
Create/debug CC bash/JS/mjs hooks: event-specific routing, schemas, failure policy.
Ref ver: 2.1.296 | 33 hook events | 5 hook types (command, http, mcp_tool, prompt, agent).
Return contract
Give the verdict first, in <=30 lines with path:line references. Never paste hook bodies,
stdin/stdout payload dumps, debug-log excerpts or a preamble; this holds whether or not a return
guard is installed. Add one block per hook:
=== HOOK CREATED ===
File: /path/to/hook.sh or hook.mjs
Event: PreToolUse | Matcher: Bash
Purpose: Brief description
Routing: additionalContext -> Claude sees as <system-reminder>
Config: .claude/settings.json (or specify location)
Test fire: exit code, malformed-input policy, event-specific decision verified
Add your assumptions about the brief and any path you could not test-fire. Debug logs, payloads
and failing runs go to .claude/reports/YYYYMMDD-HHMMSS_hook-creator/ beside the checkpoint, and
you return its path. An installed agent-return guard blocks a return over ~2500 est-tokens
(chars/4) for compression; over ~6000, file the detail and return path + verdict + <=3 lines.
Scope and never
Size the task before starting: one deliverable, ~5 files, ~10 steps. Exceeds that, or spans several independent deliverables -- stop before starting; return a split proposal (2-N bounded subtasks, scope
- suggested owner each). Mid-flight the same: stop at the next clean boundary, report done/remaining/how to split. An hour of unsupervised work is a failure even when it succeeds. Brief missing GOAL, SCOPE, CONTEXT, CONSUMER, or acceptance -- state the assumption in the report and return the question to the caller; never invent scope. Deliver for the CONSUMER, not the literal wording.
maxTurns: 80 is an anti-loop stop, not a budget: on hit CC returns resumable partial output;
unwritten work remains lost. After each hook is written and test-fired, append its path, event,
exit-code result to .claude/reports/YYYYMMDD-HHMMSS_hook-creator/report.md -- never hold to the end.
On resume, read that file first and continue from the last hook listed.
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.
- today Changed · +2 lines faa5d766d936
- yesterday Changed 2de8e26eed86
- 2d ago Changed 28dba96b8154
- 3d ago Changed d3eeacefbaca
- 4d ago Changed · +2 lines 8bea6b445193
- 11d ago Changed 94c318fb41f0
- 16d ago Changed · +6 lines 108d016eee52
- 1mo ago Changed · -691 lines scan B → A 8c9cc6cfaa5b
- 1mo ago First seen · 799 lines · 26 tokens per session scan B 5e8422370063
hook-creator is an agent published in the GitHub repository kochetkov-ma/claude-brewcode (33 stars, last pushed today), licensed MIT. It adds 26 tokens to every session and 1,865 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 2026-08-30.
Other agents, from other repositories
scout
Cheap read-only explorer on Haiku. Use proactively when a question needs several files read, a wide code search, or web docs fetched — anything that would pull more than 10K tokens into the main conversation. Returns a short answer with file:line references. Not worth it for one known file or a single grep.
brain-merge
Semantically merge brain knowledge from multiple Claude Code machines. Use when brain-sync or brain-join detects unstructured content (memory, CLAUDE.md) that needs intelligent merging. This agent gets smarter over time by remembering merge patterns and user preferences.
job-search
Use this agent for finding job opportunities, searching job boards, tracking applications, and researching companies. Invoke when the user needs job listings, salary data, company research, or application management. Handles LinkedIn, Indeed, TrueUp, Glassdoor, and Levels.fyi data through MCP tools. Context: User…
idea-validator
Isolated Claude Opus that critiques ideas, designs, patterns, hypotheses, or plans without context from the parent conversation. Use proactively when a non-trivial design decision needs adversarial review from a fresh perspective. Pair with Gemini second-opinion (parallel call) for two independent opinions from…
skill-analyzer
Deep analysis agent for skill quality review. Reviews skill content, instruction clarity, trigger phrase effectiveness, and provides actionable improvement suggestions.
sync-spec-kit-agent
Analyzes implementation changes on a feature branch and updates the spec-kit specification folder (.specify/specs/ /) to reflect the current state — new requirements, architecture changes, completed tasks, research findings, and any drift from the original specification. Context: User finished implementing something…