aar

aar is a skill for Claude Code, Codex from neurofoo/agent-skills. It costs 39 tokens per session (607 once invoked), scanned A, original, MIT.

A structured review of an important event, such as a project or incident. It compares expectations with facts about what happened, explains the difference, and identifies what to do next.

In plain words
What is it for?
Use it after projects, launches, presentations, or other significant events to capture successes, problems, causes, and follow-up actions.
Why use it?
It makes team learning more specific and constructive by focusing on evidence and systems instead of blame.

Skill for Claude CodeCodex

Part of the retrospective-skills plugin — 3 skills, 2 commands 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/neurofoo/agent-skills/aar
Any agent
npx skills add neurofoo/agent-skills --skill aar
Clone the repo
git clone --depth 1 https://github.com/neurofoo/agent-skills

Made for: Claude Code, Codex.

Or install retrospective-skills, the plugin that ships this one along with the rest of its 3 skills, 2 commands.

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 aar

README.md
[![agentmods](https://agentmods.dev/badge/skills/neurofoo/agent-skills/aar.svg)](https://agentmods.dev/skills/neurofoo/agent-skills/aar)
Your own site
<a href="https://agentmods.dev/skills/neurofoo/agent-skills/aar"><img src="https://agentmods.dev/badge/skills/neurofoo/agent-skills/aar.svg" alt="Measured on agentmods" height="20"></a>
Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 607 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 $0.00039 $0.00607
Opus 5 $0.00019 $0.00303
Sonnet 5 $0.00008 $0.00121
Haiku 4.5 $0.00004 $0.00061

Measured 5d ago against content hash 0704fde2bc21, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

aar 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.

aar/SKILL.md · 113 lines

How it starts

The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.

After-Action Review

Conduct a structured debrief to extract learning from any significant event or experience.

Instructions

Work through the four core questions honestly and specifically. Focus on events and systems, not blaming individuals.

Output Format

Event: What are we reviewing? Date: When did it happen? Participants: Who was involved?


1. What Was Expected?

Before the event, what did we think would happen?

Goals/Objectives

  • [What were we trying to achieve?]

Plan

  • [What was the plan to achieve it?]

Success Criteria

  • [How would we know if we succeeded?]

Assumptions

  • [What did we assume would be true?]

2. What Actually Happened?

Facts only—what occurred, not why

Timeline

Time Event
[When] [What happened]

Outcomes

  • [What results did we get?]

Compared to Expected

Expected Actual Gap
[expectation] [reality] [+/-]

3. Why the Difference?

Analysis of the gap between expected and actual

What Went Well (sustain these)

Success Contributing Factors
[what worked] [why it worked]

What Didn't Go Well (improve these)

Problem Root Cause
[what failed] [why it failed]

Surprises

  • [Things we didn't anticipate]

4. What Do We Do Next?

Specific actions to sustain or improve

Sustain (keep doing these)

Action Owner How to Protect It
[what to continue] [who] [mechanism]

Improve (change these)

Action Owner By When
[what to change] [who] [deadline]

Key Takeaways Top 3 lessons from this review:

  1. [Lesson]
  2. [Lesson]
  3. [Lesson]

Follow-up When will we check if improvements are working?

Guidelines

  • Do this soon—memory fades fast
  • Be specific: "Communication failed" → "We didn't update Slack until hour 3"
  • Balance: Include what went well, not just problems
  • Assign owners: Insights without ownership become forgotten
  • Make it safe: Blame shuts down honesty

Read the full file on GitHub · 113 lines

Files

What ships with it

3 files 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.

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 · 113 lines · 39 tokens per session scan A 0704fde2bc21

Subscribe to this mod's changes

aar is a skill published in the GitHub repository neurofoo/agent-skills (111 stars, last pushed 7mo ago), licensed MIT. It adds 39 tokens to every session and 607 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 2026-08-30.

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

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 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