retro

retro is a command for coding agents from brainOS-HQ/brain-os. It costs 0 tokens per session (876 once invoked), scanned A, original, MIT.

A retrospective command that examines recent project activity, current state, recurring patterns, and session notes to explain what changed and what did not.

In plain words
What is it for?
Use it for weekly or monthly reviews of projects or named entities, including shipped work, decisions, open items, and patterns.
Why use it?
It separates completed work from repeated plans, avoided tasks, and unexpected developments.

Command

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 commands/brainos-hq/brain-os/retro
Clone the repo
git clone --depth 1 https://github.com/brainOS-HQ/brain-os

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 retro

README.md
[![agentmods](https://agentmods.dev/badge/commands/brainos-hq/brain-os/retro.svg)](https://agentmods.dev/commands/brainos-hq/brain-os/retro)
Your own site
<a href="https://agentmods.dev/commands/brainos-hq/brain-os/retro"><img src="https://agentmods.dev/badge/commands/brainos-hq/brain-os/retro.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 876 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 $0.00000 $0.00876
Opus 5 $0.00000 $0.00438
Sonnet 5 $0.00000 $0.00175
Haiku 4.5 $0.00000 $0.00088

Measured 5d ago against content hash 4e135519fa59, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

retro 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.

templates/commands/retro.md · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Brain OS : Retrospective Engine

"What actually happened? What moved, what stuck, what am I avoiding?"

Not a status report. A mirror.

REQUIRED FIRST READ

Before any tool call, read ~/.claude/brain-os/PROTOCOL.md.

Input

Arguments: $ARGUMENTS (optional : entity/project name, "weekly" or "monthly", or both e.g. brain-os weekly). Defaults to weekly across all entities if no argument.

Primary tool sequence

  1. mcp__brain-os__audit_log({days: 7}) (or 30) : what was actually written, decided, updated
  2. mcp__brain-os__entity_read() : current state of all entities
  3. mcp__brain-os__pattern_detect() : active patterns
  4. mcp__brain-os__semantic_recall("this week", source_kind="session") : cross-reference session context

Analysis

Weekly retro

Look at what changed in the last 7 days. For each touched entity, compare current state to the next_move at the start of the week.

Determine:

  • Shipped: things that actually moved from plan to done
  • Decided: strategic decisions made
  • Repeated but not shipped: things mentioned in next_move / open_questions that haven't moved
  • Avoided: active entities not touched at all this week
  • Surprise: unplanned work that took priority, or an entity that moved when it wasn't supposed to

Monthly retro

Same analysis over 30 days. Plus:

  • Mode changes: entities that moved between active/parked/incubating/archived
  • Decisions that held: 30+ day old decisions still guiding work
  • Decisions that didn't hold: decisions quietly abandoned or contradicted
  • Momentum trajectory: for each active entity, momentum higher or lower than a month ago?

Output

========================================
  [WEEKLY/MONTHLY] RETRO : [date range]
========================================

  SHIPPED
  ----------------------------------------
  [entity] : [what actually moved]

  DECIDED
  ----------------------------------------
  [entity] : [decision]

  REPEATED BUT NOT SHIPPED
  ----------------------------------------
  [entity] : [thing that keeps appearing in next_move]

  NOT TOUCHED
  ----------------------------------------
  [entity] : [days since last update] : [mode]

  HIDDEN PATTERN
  ----------------------------------------
  [one honest observation about the period]

========================================
  RECOMMENDATION
========================================
  [one sentence: what next period should focus on]
  [one sentence: what to stop doing]
========================================

Read the full file on GitHub · 103 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. 5d ago First seen · 103 lines · 0 tokens per session scan A 4e135519fa59

Subscribe to this mod's changes

retro is a command published in the GitHub repository brainOS-HQ/brain-os (6 stars, last pushed 11d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 876 tokens. 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.