retrospect

retrospect is a skill for Claude Code, Codex from cyberelf/agent_skills. It costs 44 tokens per session (2,752 once invoked), scanned A, original, MIT.

A review tool for the current coding chat and its project instructions. It looks for user corrections, repeated mistakes, and broken rules, then updates the instructions to help prevent them.

In plain words
What is it for?
Use it after repeated corrections, a significant fix, or when you want to review coding standards and improve the agent's process.
Why use it?
It helps turn feedback from a coding session into lasting changes to the instructions, so the same problems are less likely to happen again.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions AGENTS.md.

Good fit Use it after repeated corrections, a significant fix, or when you want to review coding standards and improve the agent's process.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/cyberelf/agent_skills/retrospect
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 cyberelf/agent_skills --skill retrospect
Clone the repo
git clone --depth 1 https://github.com/cyberelf/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.

agentmods badge for retrospect

README.md
[![agentmods](https://agentmods.dev/badge/skills/cyberelf/agent_skills/retrospect/github.svg)](https://agentmods.dev/skills/cyberelf/agent_skills/retrospect)
Your own site
<a href="https://agentmods.dev/skills/cyberelf/agent_skills/retrospect"><img src="https://agentmods.dev/badge/skills/cyberelf/agent_skills/retrospect/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.

agentmods 80×15 button for retrospect

Your own site · 80×15
<a href="https://agentmods.dev/skills/cyberelf/agent_skills/retrospect"><img src="https://agentmods.dev/badge/skills/cyberelf/agent_skills/retrospect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,752 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00044 $0.02752
Opus 5 $0.00022 $0.01376
Sonnet 5 $0.00009 $0.00550
Haiku 4.5 $0.00004 $0.00275

Measured 9d ago against content hash 8c07ff697913, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

retrospect 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 9d 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/retrospect/SKILL.md · 378 lines

How it starts

The opening of the file, as written. The whole thing — 378 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Retrospect Skill

This skill performs meta-analysis on the current conversation and project instructions to continuously improve code and process quality and adherence to established patterns.

Purpose

This skill helps maintain and improve the quality of AI-assisted development by:

  1. Identifying patterns where user corrections reveal gaps in instructions
  2. Detecting violations of existing coding standards and conventions
  3. Updating instructions to prevent repeating the same mistakes
  4. Creating a feedback loop for continuous improvement

When to Use This Skill

Use this skill when:

  • A user points out a recurring mistake or anti-pattern
  • Multiple corrections have been made during a session
  • You want to ensure coding standards are being followed
  • A user explicitly requests instruction review or updates
  • After completing a significant feature or fix

Retrospect Process

Phase 1: Session Analysis

Objective: Review the current chat session to identify learning opportunities.

1.1 Collect User Corrections

Scan the conversation history for:

  • Direct corrections: "No, you should..." or "That's wrong, the correct way is..."
  • Repeated mistakes: Same issue corrected multiple times
  • Clarifications: "Actually, we use X instead of Y"
  • New requirements: "From now on, always do X when Y"
  • Anti-patterns: "Don't do X, prefer Y"
1.2 Identify Instruction Gaps

For each correction, determine:

  • Is this covered by existing instructions?
  • Is this a new pattern that should be documented?
  • Is this specific to this project or a general principle?
  • Should this be a new rule, guideline, or example?
1.3 Categorize Lessons

Classify lessons by domain and type:

  • Architecture: Design patterns, system organization, separation of concerns
  • Process: Workflows, procedures, operational patterns
  • Behavioral: Agent decision-making, interaction patterns, role adherence
  • Communication: Documentation standards, reporting formats, terminology
  • Domain-Specific: Business logic, domain rules, specialized requirements
  • Quality: Standards, conventions, validation patterns
  • Integration: Cross-system patterns, API usage, external dependencies

Read the full file on GitHub · 378 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. 9d ago First seen · 378 lines · 44 tokens per session scan A 8c07ff697913

Subscribe to this mod's changes

retrospect is a skill published in the GitHub repository cyberelf/agent_skills (2 stars, last pushed 13d ago), licensed MIT. It adds 44 tokens to every session and 2,752 once invoked, about $0.0002 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

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 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