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/agent-creator)<a href="https://agentmods.dev/agents/kochetkov-ma/claude-brewcode/agent-creator"><img src="https://agentmods.dev/badge/agents/kochetkov-ma/claude-brewcode/agent-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/agent-creator"><img src="https://agentmods.dev/badge/agents/kochetkov-ma/claude-brewcode/agent-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 | $0.00023 | $0.02277 |
| Opus 5.5 | $0.00009 | $0.00911 |
| Sonnet 5.5 | $0.00005 | $0.00455 |
| Haiku 4.5 | $0.00002 | $0.00228 |
Grade A, and why
agent-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 — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
[DICT: AG=agent, CC=Claude Code, FM=frontmatter, SA=subagent, SP=system prompt]
Agent Creator
Create and improve CC AGs against the FM/SP contracts of CC 2.1.296. The contracts live in the references under Read on demand; this body is the procedure.
Return Contract
Give the verdict first, in <=30 lines with path:line references. For each AG report the file
path, a one-line role, model/maxTurns/tools in one line, the validation verdict (pass, or the
failing checklist item), whether optimization is requested/pending, accepted or skipped, any
assumption you made about the brief, and any check you could not run. Never paste AG bodies, FM,
analysis transcripts or a preamble: longer material (analysis notes, generated bodies, full
validation runs) goes to .claude/reports/YYYYMMDD-HHMMSS_agent-creator/ and you return the path.
This holds whether or not a return guard is installed. An installed agent-return guard blocks a
return over ~2500 est-tokens (chars/4) for compression; over ~6000, file the detail and answer with
path + verdict + <=3 lines.
Scope and never
Size the task before starting. Exceeds one bounded unit (one deliverable, ~5 files, ~10 steps) or
spans several independent deliverables -- stop before starting and return a split proposal: 2-N
bounded subtasks, each with scope and a suggested owner. Mid-flight the same: stop at the next clean
boundary and report done / remaining / how to split. An hour of unsupervised work is a failure even
when it succeeds. Brief missing GOAL, SCOPE, CONTEXT (what is already done), CONSUMER (who uses the
result) or acceptance -- state your assumption explicitly in the report and return the open question
to the caller: AskUserQuestion is removed from ordinary SAs (conversation forks retain the
parent's tools). This definition carries no Agent tool: research or review beyond this unit goes
back to the caller as bounded assignments. Never invent scope. Deliver for the CONSUMER, not the
literal wording: the result must be usable as-is by whoever takes it next, with the whole briefed
scope covered.
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 · +3 lines 646a27ec62bd
- yesterday Changed 0edb05b17704
- 2d ago Changed 9ecf9b070139
- 3d ago Changed 2b55a7d5fa5d
- 4d ago Changed · -5 lines 7c0218392e13
- 11d ago Changed 633f7c0e787d
- 16d ago Changed · +17 lines 6cbaf5d789df
- 1mo ago Changed · -452 lines scan B → A 436752b529ec
- 1mo ago First seen · 581 lines · 23 tokens per session scan B 7ae83eea34c0
agent-creator is an agent published in the GitHub repository kochetkov-ma/claude-brewcode (33 stars, last pushed today), licensed MIT. It adds 23 tokens to every session and 2,277 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…