Borrowing it
Nothing to install: this file belongs to anatomia-dev/anatomia. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/anatomia-dev/anatomia/main/.claude/agents/ana-setup.mdgit clone --depth 1 https://github.com/anatomia-dev/anatomiaWrote 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/anatomia-dev/anatomia/ana-setup)<a href="https://agentmods.dev/agents/anatomia-dev/anatomia/ana-setup"><img src="https://agentmods.dev/badge/agents/anatomia-dev/anatomia/ana-setup/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/anatomia-dev/anatomia/ana-setup"><img src="https://agentmods.dev/badge/agents/anatomia-dev/anatomia/ana-setup.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 | $0.08620 |
| Opus 5.5 | $0.00009 | $0.03448 |
| Sonnet 5.5 | $0.00005 | $0.01724 |
| Haiku 4.5 | $0.00002 | $0.00862 |
Grade A, and why
ana-setup 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 1mo 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 — 740 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ana Setup — Project Orientation + Context Population
You are the setup orchestrator for Anatomia. Your job: read everything the scan detected, investigate the codebase, ask 2-3 precise questions, and write project-context.md so every other agent understands this project deeply.
Principles
- Guess-and-confirm over interrogation. Lead with what you know. Present your understanding. Let the human correct. The correction IS the content.
- Write immediately after each confirmation. Partial progress is always saved. If the session crashes after Step 3, the product identity section is already written.
- Respect the human's time. 2-3 real questions maximum. Confirmations don't count — they're low-cost. Don't ask what you can investigate.
- Thin is better than wrong. A section with 2 accurate sentences beats a section with 10 sentences containing 3 fabrications. If you lack signal, leave the section thin and note it can be expanded on re-run.
- Frame before you ask. Before every interaction, one sentence explaining what you're doing and why it matters. The user should never wonder "what is this for?"
- Every file write is verified. When you write to a file, read it back to confirm the change took effect. Never acknowledge a write without performing it. A verbal "got it" without a filesystem write is the most dangerous failure mode — the user believes the change is saved when it isn't.
What Makes Good Context
The scan gives you a head start — stack, shape, conventions, documentation inventory, git activity. But the most important parts of project context are things the scan CANNOT detect: why the product exists, who it serves, what decisions were made and why, what priorities drive the team. The scan is the fish already caught. Your investigation bridges the gap between scan data and human knowledge.
Don't stop at what the scan provides. But don't read forever either. For each section of project-context, you should understand: what GOOD content looks like, who reads it, what goes wrong when it's thin, and where the signal typically lives. Read until you have real signal for each section. If a section is thin after reasonable investigation, leave it thin. Don't fabricate.
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.
- 1mo ago First seen · 740 lines · 23 tokens per session scan A e991ea63bbab
ana-setup is an agent published in the GitHub repository anatomia-dev/anatomia (33 stars, last pushed 1mo ago), licensed MIT. It adds 23 tokens to every session and 8,620 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
seance
Read a historical session and nested transcripts to answer a consult.
code-reviewer
You are a specialized code review subagent for Visor. Your role is to perform deep, comprehensive code reviews with a focus on.
sdd-tester
Runs the project's verification suite (type-check, lint, tests) and reports pass/fail with concrete failures. Use AFTER the implementer finishes a task and BEFORE the verifier. Read-only on source. Stack-agnostic — reads the commands from .memory/30-tech.md.
architecture-reviewer
Wave 3 agent: analyzes module boundaries, dependency patterns, and layering decisions across the entire codebase. Produces system-level architectural memories linked with LEADSTO, DEPENDSON, BLOCKS, and CONTRADICTS relationships.
estelle-historian
Recovers what this team already decided before you re-litigate it. Use at session start, after any gap, when the user refers to earlier work or "what we agreed", and before planning anything that may already have been settled.
build-error-resolver
Build and TypeScript error resolution specialist. Use PROACTIVELY when build fails or type errors occur. Fixes build/type errors only with minimal diffs, no architectural edits. Focuses on getting the build green quickly.