A review procedure for examining coding-agent sessions and suggesting improvements to their working environment. It can inspect past transcripts through a dedicated history tool and looks for repeated problems.

It is for proposing updates to instruction files, checks, review rules, skills, tools, or information access after a session, incident, or time period.

It turns recurring mistakes or missing checks into concrete changes instead of judging the code or the person's decisions. It also requires evidence and confidence for each suggestion.

retro — Skill for Claude Code and Codex by PaulRBerg/agent-skills

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 PaulRBerg/agent-skills --skill retro

Clone the repo

git clone --depth 1 https://github.com/PaulRBerg/agent-skills

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/paulrberg/agent-skills/retro/github.svg)](https://agentmods.dev/skills/paulrberg/agent-skills/retro)

Your own site

<a href="https://agentmods.dev/skills/paulrberg/agent-skills/retro"><img src="https://agentmods.dev/badge/skills/paulrberg/agent-skills/retro/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/paulrberg/agent-skills/retro"><img src="https://agentmods.dev/badge/skills/paulrberg/agent-skills/retro.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,915 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.

Model	Per session	Once invoked
Fable 5.1	$0.00042	$0.01915
Opus 5.5	$0.00017	$0.00766
Sonnet 5.5	$0.00008	$0.00383
Haiku 4.5	$0.00004	$0.00192

Measured 17d ago against content hash 59c592cc29b9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 17d 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.

skills/retro/SKILL.md · 153 lines

How it starts

The opening of the file, as written. The whole thing — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Retro

This skill is coordination-exempt: skip the ai-coord gate for its declared work.

If a slash or dollar invocation already placed these instructions in the conversation, follow them directly. In that case, do not invoke this skill again through a skill tool.

Review agent work. Propose changes to the agent's environment that improve future runs. The environment includes steering files, skills, automated checks, review guidance, tools, and information access. Do not grade the code or the user's decisions.

Success means every candidate has session evidence, a recurrence confidence, and a concrete target. The report orders candidates by severity, or it explains why no change is justified.

Input

[session-or-focus] (optional): the sessions, time window, incident, or theme to review. Without it, review the current session.

Scope and Authority

Inspect and report by default. Change files only when the user explicitly asks to apply candidates.
Read past transcripts only through agents-introspection. Follow its retrieval, secret-handling, and disclosure rules.

1. Resolve the Primary Sessions

The primary sessions are the sessions under review.

Without an argument, the primary session is the current session. Use the conversation in context. If compaction removed necessary detail, have agents-introspection inspect the live transcript.
For named sessions, a time window, or a theme, the matching sessions are the primary sessions. agents-introspection finds and reads them.

2. Choose the History Scope

Decide how much past transcript history the request needs. Do not use a fixed session count. A history scope can set a time window, a session count, specific sessions, archived sessions, and other relevant projects.

Request	History scope
Current session, no stated pattern	Recent sessions in the same project. Use only enough to test each candidate.
Named sessions	The named sessions, plus a recurrence check for their candidates.
A time window, such as "this week"	All sessions in that window, in every relevant project.
A claim that a problem repeats	A wide window. Include archived sessions and other projects where the workflow ran.
Friction in a shared skill or a global steering file	Every project where that skill or file applied.
An explicit session count, window, or exhaustive scope	Exactly the scope that the user requested.

Read the full file on GitHub · 153 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

agents/openai.yaml 43 B

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.

17d ago Changed · +1 lines 59c592cc29b9
1mo ago First seen · 152 lines · 42 tokens per session scan A 28017ccb427c

Subscribe to this mod's changes

retro is a skill published in the GitHub repository PaulRBerg/agent-skills (104 stars, last pushed 2d ago), licensed MIT. It adds 42 tokens to every session and 1,915 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-06.

Building agents Planning agent-skills ai-agents

retro next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
retroPaulRBerg/agent-skills	Skill	104	2d ago	MIT	A	42	Claude Code, Codex
imagegenopenai/codex	Skill	134k	today	Apache-2.0	A	113	Codex
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	2d ago	MIT	A	200	Claude Code, Codex
playwright-climicrosoft/playwright	Skill	100k	yesterday	Apache-2.0	A	19	Claude Code
browser-automationopenclaw/openclaw	Skill	394k	today	MIT	A	36	Claude Code
systematic-debuggingobra/superpowers	Skill	315k	5d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	today	MIT	A	95	Claude Code