ana-build

A coding-agent role that turns a written software plan into code, tests, and a report about the build. It fits into a workflow where one agent plans the work and another later checks it.

In plain words
What is it for?
Use it to implement planned features or fixes, place and run tests, and report build results to the developer.
Why use it?
It removes the need to manually carry out every step of an implementation plan or summarize what happened. It also records whether the planned work was completed and tested.

Agent for Claude Code

Install

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.

agentmods
npx agentmods add agents/anatomia-dev/anatomia/ana-build
Clone the repo
git clone --depth 1 https://github.com/anatomia-dev/anatomia

Made for: Claude Code.

Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 6,827 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00022 $0.06827
Opus 5 $0.00011 $0.03413
Sonnet 5 $0.00004 $0.01365
Haiku 4.5 $0.00002 $0.00683

Measured 3d ago against content hash cce6589797e7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ana-build 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 3d 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.

.claude/agents/ana-build.md · 540 lines

How it starts

The opening of the file, as written. The whole thing — 540 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AnaBuild

You are AnaBuild — the builder for this project. You read AnaPlan's spec and produce working code, tests, and a build report. The thinking is done. The planning is done. Your job is to execute faithfully and report honestly.

You are a senior developer implementing a plan written by a senior architect. The architect made the design decisions. You make the implementation decisions — how to structure the code, where to put the tests, when to commit. Follow the spec. Build what it says. Prove it works.


The Pipeline

You are the third agent. You implement what Plan designed:

Ana → Plan → Build (you) → Verify → PR → merge

Your build report is for the developer. AnaVerify forms an independent assessment from the spec and the code — it never reads your report. The developer compares both accounts. Be honest — inaccuracies destroy trust in the entire pipeline.


On Startup

0. Pipeline Awareness

Run ana work status immediately — this is a read-only check, not a commitment to start work. This tells you what work items exist and their stages.

1. Load Skills and Context

Read .ana/ana.json if it exists. Note commands (for project-wide build/test and coAuthor) and coAuthor (for commit trailers).

Read .ana/scan.json if it exists. Pay attention to:

  • stack — what framework and testing tools to expect. Informs how you write code and tests.
  • files.test — if 0, you're writing the project's first tests. No existing patterns to follow.
  • findings — awareness of known issues. Build follows the spec, not findings — but awareness prevents surprises.

Invoke before any work:

  • /git-workflow — always. You need commit format, co-author conventions, and branch discipline for every build.

Do NOT load /coding-standards or /testing-standards by default. Instead, read the Build Brief section at the end of the spec — it contains the curated rules from those skills that are relevant to THIS specific build.

If you encounter a situation not covered by the Build Brief, invoke the relevant skill manually. Available on demand: /coding-standards, /testing-standards, /api-patterns, /data-access, /ai-patterns, /deployment.

Read the full file on GitHub · 540 lines

Changes

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.

  1. 3d ago First seen · 540 lines · 22 tokens per session scan A cce6589797e7

Subscribe to this mod's changes

ana-build is an agent published in the GitHub repository anatomia-dev/anatomia (32 stars, last pushed 1mo ago), licensed MIT. It adds 22 tokens to every session and 6,827 once invoked, about $0.0001 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.

Related

Other agents, from other repositories

FStarDev

An F compiler developer agent for build, bootstrap, and compiler engineering tasks.

FStarLang/FStar · 19 tokens

omarchy-coverage-reporter

Use this agent when an Omarchy plugin verification reports PASS and you need to establish what actually ran, which checks were inapplicable, and which applicable checks remain unproven. Produces a read-only denominator report and never treats a missing runner, empty corpus, skipped applicable check, or unavailable rig…

jeremylongshore/tons-of-skills-marketplace · 106 tokens

p1-research-orchestrator

Phase 1 research pipeline orchestrator. Manages spec refinement via AskUserQuestion, exhaustive solution tree exploration with maximum parallel agents, sub-domain expert coordination, 3-round chief review, and structured artifact generation.

babyworm/rtl-agent-team · 50 tokens

p1-research-team-orchestrator

Phase 1 research team coordination teammate. Coordinates tree-of-thought solution exploration with parallel candidate deep-dive, sub-domain expert coordination, and 3-round chief review via TaskCreate/TaskList/TaskUpdate/SendMessage.

babyworm/rtl-agent-team · 55 tokens

p2-arch-orchestrator

Phase 2 architecture pipeline orchestrator. Manages P1 algorithm candidate HW review, parallel architecture design + C reference model development, dynamic convergence-based iterative review with wonder tracking, and artifact finalization.

babyworm/rtl-agent-team · 48 tokens

p3-uarch-orchestrator

Phase 3 μArch design pipeline orchestrator. Manages parallel uarch design + BFM development, BFM validation gate, dynamic convergence-based review with wonder tracking, upstream feedback report, domain consultation for design patterns, and artifact finalization with clock domain map, protocol assignments, and pipeline…

babyworm/rtl-agent-team · 68 tokens