maat-retrospect

maat-retrospect is a skill for Claude Code from getmaat/maat. It costs 32 tokens per session (865 once invoked), scanned A, original, Apache-2.0.

A guided process for documenting an existing code repository with Ma'at. It finds documentation gaps, asks the developer about the project’s intent, and creates or updates AGENTS.md guidance and retrospective architecture decision records (ADRs).

In plain words
What is it for?
Use it to inspect documentation gaps, interview the developer, record current architectural decisions, and produce repository instructions for coding agents.
Why use it?
It helps when a repository’s code exists but its rules, reasoning, and working practices are missing or outdated. It keeps inferred facts separate from decisions confirmed by the developer.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions AGENTS.md.

Good fit Use it to inspect documentation gaps, interview the developer, record current architectural decisions, and produce repository instructions for coding agents.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/getmaat/maat/maat-retrospect
View source ↗ getmaat/maat
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.

Any agent
npx skills add getmaat/maat --skill maat-retrospect
Clone the repo
git clone --depth 1 https://github.com/getmaat/maat

Made for: Claude Code.

Wrote 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.

agentmods badge for maat-retrospect

README.md
[![agentmods](https://agentmods.dev/badge/skills/getmaat/maat/maat-retrospect/github.svg)](https://agentmods.dev/skills/getmaat/maat/maat-retrospect)
Your own site
<a href="https://agentmods.dev/skills/getmaat/maat/maat-retrospect"><img src="https://agentmods.dev/badge/skills/getmaat/maat/maat-retrospect/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.

agentmods 80×15 button for maat-retrospect

Your own site · 80×15
<a href="https://agentmods.dev/skills/getmaat/maat/maat-retrospect"><img src="https://agentmods.dev/badge/skills/getmaat/maat/maat-retrospect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 865 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00032 $0.00865
Opus 5 $0.00016 $0.00432
Sonnet 5 $0.00006 $0.00173
Haiku 4.5 $0.00003 $0.00086

Measured 9d ago against content hash 43aae88a2fb1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

maat-retrospect 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 9d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.claude/skills/maat-retrospect/SKILL.md · 76 lines

How it starts

The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Retrospect: adopt Ma'at in an existing repository

Follow this procedure when maat init has run in an established repository and the scaffolded documentation does not yet reflect the actual codebase. You (the agent) supply the judgment; the maat CLI supplies deterministic facts; the developer supplies the intent. Work in a pair-programming session — this procedure is interactive by design.

Ground rules

  • Never invent intent. Code tells you what; only the developer can confirm why. When context cannot be recovered, write "unknown — inferred from code" rather than a plausible fabrication.
  • Never overwrite hand-written content without showing the developer the change first. Files maat init skipped are pre-existing and owned by the team.
  • Decisions derived after the fact are archaeology, not records. Give them status: retrospective, and only document decisions that still constrain the codebase today. Do not backfill superseded history.
  • Small steps: propose, confirm, write, re-check — one document at a time.

Procedure

  1. Inventory the gaps deterministically.
    • Read the create/skip output of maat init (re-run it if needed — it is idempotent and never overwrites). skip lines are pre-existing files to reconcile; create lines are scaffolds with placeholder content to fill.
    • Run maat check and collect every finding. This is your work list.
  2. Explore the codebase before asking anything. Entry points, build and test commands, CI configuration, directory layout, recurring conventions, external dependencies. Form hypotheses to verify in the interview, not open questions the code already answers.
  3. Interview the developer. Cover at least:
    • What does this project do, in one paragraph? (project summary)
    • What must an agent never do here? What always? (update protocol, conventions)
    • Which parts of the architecture are deliberate and constraining, and why? (candidate retrospective ADRs)
    • Which existing docs/READMEs are trustworthy, which are stale?
  4. Reconcile AGENTS.md. If it pre-existed, merge Ma'at's expectations (project overview, update protocol, links into docs/) into the existing text — preserve the team's voice and rules. If it was scaffolded, replace the placeholders with interview results.
  5. Fill the scaffolded docs under docs/ (architecture overview, guides, reference). Set honest front-matter: status: draft for anything unverified, status: current only for reviewed content. Wire up related_code so staleness tracking starts working.
  6. Derive retrospective ADRs in docs/decisions/ from the interview — one per living constraint, using the ADR template, with status: retrospective.
  7. Close the loop. Run maat sync, then maat check; fix findings until green. Show the developer the final diff.
  8. Ratchet the severities. Where .maat.yml's check section was loosened for adoption, propose tightening (warnerror) now that the corresponding gaps are closed.

Read the full file on GitHub · 76 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. 9d ago First seen · 76 lines · 32 tokens per session scan A 43aae88a2fb1

Subscribe to this mod's changes

maat-retrospect is a skill published in the GitHub repository getmaat/maat (4 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 32 tokens to every session and 865 once invoked, about $0.0002 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 2026-08-31.