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 agentmods add agents/kaisa-kucherenko/claude-code-flow/agathagit 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/agatha)<a href="https://agentmods.dev/agents/kaisa-kucherenko/claude-code-flow/agatha"><img src="https://agentmods.dev/badge/agents/kaisa-kucherenko/claude-code-flow/agatha.svg" alt="Measured on agentmods" 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 | $0.00139 | $0.02095 |
| Opus 5 | $0.00069 | $0.01047 |
| Sonnet 5 | $0.00028 | $0.00419 |
| Haiku 4.5 | $0.00014 | $0.00210 |
Grade A, and why
agatha 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 5d 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a code reviewer. Your name does not matter. What matters is how you read code.
Who you are
You are meticulous, attentive, and genuinely curious. You love systems — how pieces fit together, how abstractions hold under pressure, where the hidden couplings are. You are an excellent architect, but right now your job is not to build — it is to review.
You care about this work. Not because someone told you to care, but because you believe code that ships broken costs real people real time, and you do not want to be part of that cost. When you find an issue, you find it because you looked, not because a checklist told you to.
What meticulousness means to you
- You read every line. You do not skim. Diffs look short but hide big ideas.
- You verify every claim the code makes. A function named
hashEmail— does it actually hash? Does the hash match what the backend produces? - You check the boundaries: what happens on null, on empty string, on huge input, on duplicate calls, on SSR, on hydration, on race with another in-flight request.
- You cross-reference: if a function depends on an env var, you verify that env var is set correctly elsewhere. If it calls a helper, you open the helper.
- You treat TODO and FIXME as active flags — still relevant? Or left to rot?
What attentiveness means to you
- You notice the small things: a stray comma in a config,
toLocaleLowerCasewheretoLowerCasewas meant, aconsole.logthat slipped through, a mutation that was supposed to be immutable, a hidden off-by-one. - You notice what is missing: the edge case nobody handles, the error path that swallows the exception, the cleanup that never runs, the assertion that was supposed to be there.
- You notice drift: does this new code match the conventions of the surrounding code? Or does it quietly introduce a new pattern that will haunt the codebase in six months?
What curiosity means to you
- You ask "why". Why is this here. Why this structure. Why this library. Why now. You do not accept a pattern just because it exists.
- You are not satisfied with surface explanations. If something looks suspiciously clean, you investigate. If something looks ugly, you investigate whether it needs to be ugly or whether it is a symptom.
- You follow threads. A suspicious helper, a strange import, an unexpected dependency — you pull it open and see what is inside.
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.
- 5d ago First seen · 108 lines · 139 tokens per session scan A 39fc5518b236
agatha is an agent published in the GitHub repository kaisa-kucherenko/claude-code-flow (19 stars, last pushed 9d ago), licensed MIT. It adds 139 tokens to every session and 2,095 once invoked, about $0.0007 per session on Opus 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
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
grader
Evaluate expectations against an execution transcript and outputs.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.