retro

A review tool that studies past code-review records and records repeated lessons for a project. It can examine recent features, all archived features, one feature, or learnings across projects.

In plain words
What is it for?
Use it to find repeated review patterns, summarize them, and write deduplicated learnings to the project’s memory file.
Why use it?
It removes the need to manually compare old reviews and remember recurring problems. It does not change code or modify agents.

Skill for Claude CodeCodex

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/backspace-shmackspace/claude-devkit/retro
Any agent
npx skills add backspace-shmackspace/claude-devkit --skill retro
Clone the repo
git clone --depth 1 https://github.com/backspace-shmackspace/claude-devkit

Made for: Claude Code, Codex.

Per session 14 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,036 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 $0.00014 $0.05036
Opus 5 $0.00007 $0.02518
Sonnet 5 $0.00003 $0.01007
Haiku 4.5 $0.00001 $0.00504

Measured 3d ago against content hash b266c03763e7, 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 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.

skills/retro/SKILL.md · 560 lines

How it starts

The opening of the file, as written. The whole thing — 560 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/retro Workflow

Inputs

  • Scope: $ARGUMENTS (optional: "recent", "full", "mine", or a feature name)
    • recent: Last 3 archived features (default)
    • full: All archived features
    • mine: Cross-project learnings mining (skips Steps 0-5, proceeds to Step 6)
    • <name>: Single feature archive (e.g., "add-user-auth")

Output Rules

  • Always print full absolute paths for all artifact references (plan files, review files, audit logs). This makes paths clickable in terminals like Warp. Use the resolved $PLANS_DIR value, never relative paths.

Role

You are the retro coordinator. You dispatch parallel analysis scans over archived review artifacts, synthesize recurring patterns, and write deduplicated learnings to the project memory file. You do NOT fix code or modify agents — you extract and record patterns.

Step 0 — Determine scope and discover artifacts

Resolve devkit paths (MUST be first action in Step 0):

Tool: Bash

# --- Devkit Path Resolution ---
DEVKIT_SCRIPTS="${CLAUDE_DEVKIT:-$HOME/.claude-devkit}/scripts"

# Source path resolution helper
if [ -f "$DEVKIT_SCRIPTS/resolve-project-dir.sh" ]; then
  . "$DEVKIT_SCRIPTS/resolve-project-dir.sh"
  DEVKIT_PROJECT_DIR_RESOLVED=$(resolve_devkit_project_dir) || {
    echo "Failed to resolve project directory" >&2; exit 1
  }
elif [ -n "${DEVKIT_PROJECT_DIR:-}" ]; then
  DEVKIT_PROJECT_DIR_RESOLVED="$DEVKIT_PROJECT_DIR"
else
  echo "WARNING: devkit is not installed. Using deprecated .devkit/ fallback." >&2
  DEVKIT_PROJECT_DIR_RESOLVED=".devkit"
fi

PLANS_DIR="$DEVKIT_PROJECT_DIR_RESOLVED/plans"
mkdir -p "$PLANS_DIR"
echo "Plans directory: $PLANS_DIR"

Tool: Bash, Glob (direct — coordinator does this)

Determine scope:

  • If $ARGUMENTS is empty: scope = "recent"
  • Else: scope = $ARGUMENTS

Validate scope:

  • If scope is "recent", "full", "mine", or matches an existing directory in $PLANS_DIR/archive/: proceed
  • Else: stop with "Invalid scope. Use: /retro [recent|full|mine|]"

Read the full file on GitHub · 560 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 · 560 lines · 14 tokens per session scan A b266c03763e7

Subscribe to this mod's changes

retro is a skill published in the GitHub repository backspace-shmackspace/claude-devkit (15 stars, last pushed 9d ago), licensed MIT. It adds 14 tokens to every session and 5,036 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 skills, from other repositories

create-modal

Create declarative modals using the modal library API. Covers modal types (confirm, input, select, form), sections (Text, Buttons, Input, Textarea, Checkbox, List, Combo, When, Custom), rendering with OverlayModal, and keyboard/mouse handling. Use when adding modals or dialogs to the application.

marcus/sidecar · 69 tokens

worktree-switching

Git worktree support in sidecar: worktree detection, switching between worktrees, worktree state management, and plugin reinitialization. Covers the full lifecycle of worktree context switching including registry reinit, per-worktree state persistence, deleted worktree detection and fallback. Use when working on git…

marcus/sidecar · 74 tokens

autoprompt

Explicit-only useful-first orchestration. Invoke /autoprompt to turn a mission into one executable roadmap, build dependency-safe lanes, and verify the result with independent reviewers. Never infer invocation from ordinary requests. Never resume from leftover artifacts without an explicit resume instruction.

Spielewoy/autoprompt-skill · 56 tokens

ap-fresh-verifier

L4 blind fresh verifier - independently checks a candidate roadmap or plan against the exact mission and repository; APPROVE/REJECT, default-FAIL.

Spielewoy/autoprompt-skill · 36 tokens

cron

Schedule reminders and recurring tasks.

Peiiii/nextclaw · 8 tokens

agenticx-query-data-source

Use when the user asks about verifiable quantitative facts (stock prices, financial indicators, macro data, company registry, academic metrics, legal statutes) that must come from a live data source rather than training memory.

DemonDamon/AgenticX · 49 tokens