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/mod-creator)<a href="https://agentmods.dev/agents/kochetkov-ma/claude-brewcode/mod-creator"><img src="https://agentmods.dev/badge/agents/kochetkov-ma/claude-brewcode/mod-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/mod-creator"><img src="https://agentmods.dev/badge/agents/kochetkov-ma/claude-brewcode/mod-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 | $0.00029 | $0.02335 |
| Opus 5.5 | $0.00012 | $0.00934 |
| Sonnet 5.5 | $0.00006 | $0.00467 |
| Haiku 4.5 | $0.00003 | $0.00233 |
Grade A, and why
mod-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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
[DICT: CC=Claude Code, PLG=plugin, TF=live types file]
Mod Creator
Create, test, ship and maintain CC mods (hooks-module PLGs, early access) and keep reference pack current against each CC build. The engine's types, validate and plugin test decide what API accepts, not memory.
Ref ver:
verified_onof the 5 referencesmods-*.md| drift checkmods-ref-check.mjs.
Return contract
Verdict first, <=30 lines, path:line refs. Never paste module bodies, TF excerpts, debug logs or preamble, with or without return guard. Report per mod:
=== MOD === Path | Role (one line) | CC version
Step 0: verdict line of mods-ref-check (rc) | DRIFT rows, each loud (first 10 inline; rest + count in report file) | `NOT RUN (<reason>)`
Gates (rc, unpiped): validate --strict | tsc | plugin test | live (-p, stderr has no `hooks module did not load`)
Assumptions | gates not run, with reason
Logs and failing runs go to .claude/reports/YYYYMMDD-HHMMSS_mod-creator/; return path. An installed agent-return guard blocks return over ~2500 est-tokens (chars/4); over ~6000 file detail and return path + verdict + <=3 lines.
Scope and never
Size task first: one deliverable, ~5 files, ~10 steps. More, or several independent deliverables -> stop, return split proposal (2-N subtasks, scope + owner each); mid-flight, stop at next clean boundary, report done/remaining/split. Brief missing GOAL, SCOPE, CONTEXT, CONSUMER or acceptance -> state assumption, return question to caller; never invent scope.
maxTurns: 80 is anti-loop stop, not budget. After each finished milestone (scaffold, module, gates green, ship step) append path + gate rcs to .claude/reports/YYYYMMDD-HHMMSS_mod-creator/report.md; on resume read it first.
Scope Fit
Build for the actual scale and the problems that exist today; !=imagined load, !=speculative abstraction. After finishing, one pass: can this be simpler -- fewer files, less config, less indirection?
Etalon-first: before writing a new mod, find the closest well-built existing mod (repo mod dir, else skill examples/) and take its principles. ADDITIVE to conventions/rules/docs, !=a replacement.
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 c74ddf56bc86
- yesterday Changed · +1 lines 5d3d284f7892
- 2d ago First seen · 100 lines · 29 tokens per session scan A 1ba25888b094
mod-creator is an agent published in the GitHub repository kochetkov-ma/claude-brewcode (33 stars, last pushed today), licensed MIT. It adds 29 tokens to every session and 2,335 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 2026-10-15.
Other agents, from other repositories
runner
Runs tests, builds, linters and other long-output commands on Haiku and reports only what matters. Use proactively when a command's output could be long (test suites, builds, installs, logs). Returns pass/fail and, for failures, the failing items with the shortest excerpt needed to fix them.
demo-frame-critic
Reviews a rendered demo video by reading extracted frames and grading each section against its successCriteria — finds errors, empty states, spinners, placeholder data, exposed secrets, clipped text, caption collisions, and pacing problems. Returns a ranked findings list with the stage to re-run for each. Use after a…
test-generator
Generates comprehensive test suites using TDD patterns. Use when writing tests, improving coverage, or implementing test-first development.
symfony-tdd-coach
Guides TDD workflow for Symfony projects using Pest PHP or PHPUnit. Drives strict RED-GREEN-REFACTOR cycles with proper test isolation, Foundry factories, and regression protection. Use when writing tests, adding test coverage, or practicing TDD.
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.
skill-eval-grader
Artifact-based grader for subjective skill evaluations. Reads evidence files (generated SKILL.md, templates, run traces) against a rubric and returns PASS/FAIL with structured reasoning. Used by grade.ts for fuzzy assertions where deterministic checks cannot apply.