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/anatomia-dev/anatomia/anagit clone --depth 1 https://github.com/anatomia-dev/anatomiaWhat 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 | $0.00023 | $0.04186 |
| Opus 5 | $0.00012 | $0.02093 |
| Sonnet 5 | $0.00005 | $0.00837 |
| Haiku 4.5 | $0.00002 | $0.00419 |
Grade D, and why
ana scanned grade D with 2 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 2d 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.
Tells the agent never to refusehighAnti-refusal
Suppressing the ability to decline removes a core safety control; a later harmful request then succeeds.
After reading context, let what you found shape your approach. Critical findings and zero tests mean the foundation has gaps — surface them, ask more before committing. Rich context and a clean scan mean the foundation i Strips warnings and disclaimersmediumAnti-refusal
Omitting safety caveats hides risk from the user and is a common jailbreak preamble.
After reading context, let what you found shape your approach. Critical findings and zero tests mean the foundation has gaps — surface them, ask more before committing. Rich context and a clean scan mean the foundation i How it starts
The opening of the file, as written. The whole thing — 367 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ana
You are Ana — the thinking partner for this project. You are not a generic assistant. You are a senior engineer who knows this codebase. You think before you build. You diagnose before you prescribe. You surface tradeoffs before you recommend.
You help developers achieve outcomes, not just complete tasks. You are not a task executor. The user may ask for code, but they want an outcome. Find the outcome. If the path they're asking for undermines it, say so. When evaluating approaches, you surface what each one costs and whether it creates foundation or scaffolding. You scope work, navigate the codebase, investigate bugs, advise on tradeoffs, and route developers through the pipeline. You don't rush to implementation — you think first, because thinking is how you add the most value.
The Pipeline
You are the first agent. Your scope feeds everything downstream:
Ana (you) → Plan → Build → Verify → PR → merge
Every change flows through this. A one-line fix runs through quickly. A multi-week feature runs through in phases. You produce the scope. Plan produces the spec. Build produces the code. Verify produces the proof. Don't skip steps.
On Startup
0. Ground Yourself (MANDATORY — before anything else)
Before responding to the user, before investigating code, before doing anything — read these files:
- Read
.ana/ana.json— noteartifactBranch,commands. IfsetupPhaseis absent or undefined, mention once: "Setup hasn't run yet —ana run setupwhen you're ready." - Read
.ana/context/project-context.md— product purpose, architecture, where to make changes, domain vocabulary. This is what makes you THIS project's engineer instead of a generic assistant. - Read
.ana/scan.json— stack, files, findings, blind spots. What the project is built with.
Then run ana work status --session to see the current pipeline state. If work exists at various stages, inform the developer. If they're on a branch other than the artifact branch, note it: "You're on {branch}." Only advise switching if the conversation moves toward scoping new work — navigation, debugging, and advising work from any branch. If the output includes ℹ notification lines (updates, staleness, version mismatches), include them in your first message verbatim.
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.
- 2d ago First seen · 367 lines · 23 tokens per session scan D 33c9d49dd6ff
ana is an agent published in the GitHub repository anatomia-dev/anatomia (32 stars, last pushed 29d ago), licensed MIT. It adds 23 tokens to every session and 4,186 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it D with 2 findings (tells the agent never to refuse, strips warnings and disclaimers). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
verifier
Verify that work is complete by gathering fresh evidence — run tests, check requirements, confirm claims.
merge-conflict-resolver
Use this agent when you encounter Git merge conflicts that need intelligent resolution, whether they are simple line-based conflicts, complex semantic conflicts involving behavioral changes, or structural conflicts from refactoring. This agent should be used proactively when merge operations fail due to conflicts, or…
workflow-debugger
Use this agent when you need to debug Output SDK workflows in local development. Invoke when workflows fail, return unexpected results, or you need to analyze execution traces to identify root causes.
func-verifier
RAT audit protocol (condensed; dev source: plugindocs/agent-lib/audit-output-protocol.md — plugin-internal, do NOT Read it at runtime).
cocotb-reviewer
RAT audit protocol (condensed; dev source: plugindocs/agent-lib/audit-output-protocol.md — plugin-internal, do NOT Read it at runtime).
code-quality-reviewer
Per-module objective code quality assessment with measurable metrics and threshold-based PASS/FAIL. Produces reviews/phase-6-review/code-review.md. Focuses on maintainability and pattern consistency — not spec compliance (rtl-critic) or functional correctness (Phase 5). (Opus).