agentmods.dev

retro

retro is a skill for Claude Code, Codex from MountainUnicorn/add. It costs 22 tokens per session (4,193 once invoked), scanned A, original, MIT.

A project review tool that gathers information from recent coding sessions and organizes it into tables for a person to check and refine.

In plain words
What is it for?
Use it to review a project after a chosen period, collect lessons from previous work, and create either an interactive review or a quick summary for an agent.
Why use it?
It reduces the need to remember what happened during development or search through old notes. It also separates instructions from observations so the review is easier to assess.

Skill for Claude CodeCodex

Installs and runs on its own, but its text points at files inside the plugin that ships it — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed.

not rated 11 1mo ago A scan 22 tokens original MIT
View the source file MountainUnicorn/add
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 skills/mountainunicorn/add/retro
Any agent
npx skills add MountainUnicorn/add --skill retro
Clone the repo
git clone --depth 1 https://github.com/MountainUnicorn/add

Made for: Claude Code, Codex.

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/skills/mountainunicorn/add/retro.svg)](https://agentmods.dev/skills/mountainunicorn/add/retro)
Your own site
<a href="https://agentmods.dev/skills/mountainunicorn/add/retro"><img src="https://agentmods.dev/badge/skills/mountainunicorn/add/retro.svg" alt="Measured on agentmods" height="20"></a>
Per session 22 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,193 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 $0.04193
Opus 5 $0.00011 $0.02096
Sonnet 5 $0.00004 $0.00839
Haiku 4.5 $0.00002 $0.00419

Measured 4d ago against content hash 82f0945fd28b, 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 4d 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.

core/skills/retro/SKILL.md · 414 lines

How it starts

The opening of the file, as written. The whole thing — 414 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ADD Retro Command v{{VERSION}}

Context-aware retrospective that auto-gathers data, classifies human directives and agent observations into scoped tables, and presents pre-populated findings for the human to refine — not recall from scratch.

Two modes:

  • Interactive retro (default) — Data-driven review with pre-populated tables
  • Agent summary (--agent-summary) — Quick non-interactive observations review

Pre-Flight

  1. Read .add/config.json for project context (name, maturity, stack)
  2. Read all 3 knowledge tiers: a. Tier 1: Read ${CLAUDE_PLUGIN_ROOT}/knowledge/global.md b. Tier 2: Read ~/.claude/add/library.json (fall back to library.md) c. Tier 3: Read .add/learnings.json (fall back to learnings.md)
  3. Read ~/.claude/add/profile.md if it exists
  4. Determine the retro window:
    • If --since provided, use that date
    • If previous retro exists in .add/retros/, use that date as start
    • Otherwise, use project creation date from config
  5. Check for session handoff — per the Session-Handoff Preflight in ${CLAUDE_PLUGIN_ROOT}/references/skill-epilogue.md

Mode 1: Interactive Retro (default)

Phase 1: Detect Session Context

Determine how the human spent the retro window:

  1. Read .add/away-logs/ — count away sessions, total autonomous hours
  2. Read git log — count commits, branches, PRs merged
  3. Read .add/handoff.md — check for interactive session indicators
  4. Classify context:
    • Autonomous: >70% of retro window was away-mode sessions
    • Collaborative: <30% away-mode, active interactive exchanges
    • Mixed: between 30-70% away-mode

The context classification affects the flow:

  • Autonomous: Human has less context → skip "what went well", reduce questions
  • Collaborative/Mixed: Full question set

Phase 2: Auto-Gather Metrics

Collect data for the retro window from all sources:

  • Git log: commit count, branches merged, PRs
  • Specs: count completed (status: Complete) in specs/
  • Learnings: count new entries in .add/learnings.json since last retro (by date field)
  • Workstation learnings: count new entries in ~/.claude/add/library.json since last retro
  • Observations: read .add/observations.md entries since last retro
  • Away logs: count sessions, total duration from .add/away-logs/
  • Handoff: current state from .add/handoff.md

Read the full file on GitHub · 414 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. 4d ago First seen · 414 lines · 22 tokens per session scan A 82f0945fd28b

Subscribe to this mod's changes

retro is a skill published in the GitHub repository MountainUnicorn/add (11 stars, last pushed 1mo ago), licensed MIT. It adds 22 tokens to every session and 4,193 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.

Project managementagent-driven-developmentai-agentsclaude-codemethodologypluginsdlc
Related

Other skills, from other repositories

flow-next-pilot

Single-tick autonomous build-loop conductor. One spec or the backlog, one stage per tick (pipeline.chainStages chains qa into make-pr), emits PILOTVERDICT. Use when asked to pilot a spec or backlog.

gmickel/flow-next · 49 tokens

backlog

Read, work, and maintain a Git repo's deferred-work items in docs/backlog/, one file per item. Use when the user says "backlog", "check backlog", "what's on my backlog", "work the backlog", "address the backlog", "add to backlog", "clean up backlog", or when a review or task produced items that are real but not being…

umputun/cc-thingz · 96 tokens

backlog

EXPERIMENTAL. Use when working the project-wide out-of-scope backlog at paad/code-reviews/backlog.md — cleaning it of entries that are already fixed or gone, or picking the next entry and fixing it end-to-end. Not for producing backlog entries — that is /agentic-review — and not for reviewing a branch diff.

Ovid/paad · 73 tokens

sync-project-docs

Usar para sincronizar la documentación viva del proyecto después de una fase. También: actualizar docs/project, índice, architecture.md, compliance.md, threat-model.

686f6c61/alfred-dev · 37 tokens

graduate-backlog

Graduate a project's in-repo backlog (roadmap phases, sprint deliverables, ADRs) onto a forge issue tracker at a thin-hybrid default, once the backlog outgrows a single contributor. Use when a team needs to see and claim work that currently lives only in docs/roadmap and docs/sprints, when a repo has a mature in-repo…

jrjsmrtn/project-orchestration-skills · 124 tokens

st-setup-project

Smalltalk (Pharo/Squeak) project boilerplate creator. Use when the user asks to create a new Pharo/Smalltalk project from scratch, when project structure is missing (no src/ directory or .project file), when the user wants to start a new Smalltalk development project, or when setting up BaselineOf, Core, and Tests…

mumez/smalltalk-dev-plugin · 80 tokens