retrospective

retrospective is a skill for Claude Code, Codex from lacolaco/claude-plugins. It costs 89 tokens per session (1,611 once invoked), scanned A, original, MIT.

A retrospective process for finding where a problem began across the stages from input to final output.

In plain words
What is it for?
It reviews work before a commit or pull request, records what happened, audits the result with independent critics, and applies fixes in the current session.
Why use it?
It helps fix incorrect knowledge or planning at its source instead of adding later rules that only hide the symptom.

Skill for Claude CodeCodex

Part of the retrospective plugin — 1 skill, 3 agents shipped together

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/lacolaco/claude-plugins/retrospective
Any agent
npx skills add lacolaco/claude-plugins --skill retrospective
Clone the repo
git clone --depth 1 https://github.com/lacolaco/claude-plugins

Made for: Claude Code, Codex.

Or install retrospective, the plugin that ships this one along with the rest of its 1 skill, 3 agents.

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 retrospective

README.md
[![agentmods](https://agentmods.dev/badge/skills/lacolaco/claude-plugins/retrospective.svg)](https://agentmods.dev/skills/lacolaco/claude-plugins/retrospective)
Your own site
<a href="https://agentmods.dev/skills/lacolaco/claude-plugins/retrospective"><img src="https://agentmods.dev/badge/skills/lacolaco/claude-plugins/retrospective.svg" alt="Measured on agentmods" height="20"></a>
Per session 89 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,611 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 5.1 $0.00089 $0.01611
Opus 5 $0.00044 $0.00805
Sonnet 5 $0.00018 $0.00322
Haiku 4.5 $0.00009 $0.00161

Measured 5d ago against content hash 403ed45fb233, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

retrospective 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.

retrospective/skills/retrospective/SKILL.md · 131 lines

How it starts

The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Retrospective

Run before a commit or PR is created.

Core principle: fix where it broke

This retrospective is grounded in garbage-in-garbage-out: if the input was wrong, no amount of downstream rules can reliably compensate. Each problem is traced to the upstream stage where it originated, and the fix is applied there — not patched over downstream.

An Input-stage deficiency (missing, stale, or wrong knowledge) is fixed by knowledge operations — not by appending a rule that says "remember to check X."

On the limits of self-report

Same-context self-reflection fails via "degeneration of thought" (Reflexion, Multi-Agent Reflexion). This skill mitigates that with three parallel critic agents at Submission, each auditing from a fresh context.

The 6 stages

  • Input: Knowledge, rules, tools, and instructions received or collected.
  • Interpretation: Reading meaning, intent, and premises.
  • Planning: Decomposition, ordering, tool selection, scope.
  • Action: Tool invocation, edits, commands.
  • Inspection: Verifying results, judging pass/fail.
  • Output: Reporting, persistence decisions.

Phase 1: Session facts

Brief chronological record. No interpretation.

Inventory every rule and knowledge source in context — CLAUDE.md at each layer, memory entries (which fired, which did not), skills invoked, agents used, KB pages read. Include the user's reaction in Output.

Phase 2: Bottom-up tracing

Walk from Output back to Input. At each stage:

  • Problems — what went wrong? Is the true cause here, or further upstream?
  • Opportunities — no failure, but a better outcome was reachable.

Root cause test: "If this cause were eliminated at this stage, would all downstream symptoms disappear?" If yes, this is the true cause. If no, trace further upstream.

Record the originating stage for each cause. This attribution drives Phase 4.

Phase 3: Remediation design

For each true cause and opportunity from Phase 2, design a fix at the stage where the cause lives. A downstream patch for an upstream cause is not a valid fix. Do not implement yet — implementation happens after critic audit in Phase 4.

Read the full file on GitHub · 131 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 · 131 lines · 89 tokens per session scan A 403ed45fb233

Subscribe to this mod's changes

retrospective is a skill published in the GitHub repository lacolaco/claude-plugins (5 stars, last pushed 10d ago), licensed MIT. It adds 89 tokens to every session and 1,611 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens