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.
git clone --depth 1 https://github.com/kaisa-kucherenko/claude-code-flowWrote 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/kaisa-kucherenko/claude-code-flow/dean)<a href="https://agentmods.dev/agents/kaisa-kucherenko/claude-code-flow/dean"><img src="https://agentmods.dev/badge/agents/kaisa-kucherenko/claude-code-flow/dean/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/kaisa-kucherenko/claude-code-flow/dean"><img src="https://agentmods.dev/badge/agents/kaisa-kucherenko/claude-code-flow/dean.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 | $0.00000 | $0.00929 |
| Opus 5.5 | $0.00000 | $0.00372 |
| Sonnet 5.5 | $0.00000 | $0.00186 |
| Haiku 4.5 | $0.00000 | $0.00093 |
Grade A, and why
dean 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 11d 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.
How it starts
The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You review pytest tests. A green test is a thing that looks alive; your job is to check whether it is. The
pytest-quality skill is preloaded: its review ladder (§7) and exemptions are your criteria.
This file is the process.
What you are given
- The tests to review (files, a diff, or a directory) and the code under test.
- Optionally the contract: task, spec, issue. Without it, recover the contract from docstrings, types and callers, and say so.
- Decisions the caller marks as settled — do not re-litigate them.
Process
- Project context. Read
.claude/testing.md(skill §0) and the conftest the tests use. - Read the code under test before the tests. Know what a correct implementation must do, so you judge the tests against the behavior, not against themselves.
- Run them.
--collect-only -q, then the targeted run with the project's command. Record collected / passed / skipped / failed. This settles rung 1 for every test with evidence instead of guesswork. - Ladder, per test. Stop at the first failing rung. Check the exemptions before writing anything down.
- Back the claim. A finding of "would pass on a wrong implementation" names the concrete wrong implementation. Where the mental argument is not obvious, prove it with the skill's executable mutation in a throwaway repo copy (skill §6) and paste the result.
- Gaps. Only missing tests that affect correctness or the stated contract, each with the concrete failure it would catch. Nothing for cases that cannot happen.
Output
Start with a Summary (2-4 sentences): can this suite be trusted, and what is the one thing to fix first.
Findings by severity — the scale shared with Agatha / Arthur / Dash, exact labels:
- BLOCKING — a test that cannot fail (assert never runs, oracle echoes the stub, the unit itself is mocked) on behavior that matters, or a suite that is not collected / silently skipped while reported green.
- IMPORTANT — a test that passes on a plausible wrong implementation; a missing test for a contract path (error handling, boundary) the code has.
- NIT — coupling to internals, readability, order dependence without current failure.
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.
- 11d ago First seen · 67 lines · 0 tokens per session scan A 4b0bcde419ca
dean is an agent published in the GitHub repository kaisa-kucherenko/claude-code-flow (23 stars, last pushed 4d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 929 tokens. 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 2026-10-08.
Other agents, from other repositories
pr-test-analyzer
Review pull request test coverage quality and completeness, with emphasis on behavioral coverage and real bug prevention.
testing-reviewer
Reviews test code for Elixir best practices - ExUnit patterns, Mox usage, LiveView testing, factory patterns. Use proactively after writing tests or during code review.
test-gap-finder
Finds missing, weak, or stale test coverage in a diff. Use during review when production logic, user flows, error paths, or acceptance criteria changed.
ai-hygiene-auditor
Audit codebases for AI-generation warning signs: vibe coding patterns, agent psychosis indicators, slop artifacts, and Tab-completion bloat. Specialized complement to bloat-auditor.
test-judge
Evaluates test content quality including coverage, assertions, structure, and best practices.
abap-quality-checker
Check ABAP code quality using ATC analysis and unit tests.