A team-retrospective command that reviews shared notes and agent records to find recurring problems, outdated information, successes, and missing tools.

Use it to review agent memories, suggest stale notes for removal, examine tool effectiveness, propose new tools, and update shared knowledge.

It turns past work into updated team knowledge and highlights issues that keep returning or capabilities the team lacks.

retro — Command for Claude Code by isaacsight/kernel

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.

Clone the repo

git clone --depth 1 https://github.com/isaacsight/kernel

Made for: Claude Code.

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/commands/isaacsight/kernel/retro/github.svg)](https://agentmods.dev/commands/isaacsight/kernel/retro)

Your own site

<a href="https://agentmods.dev/commands/isaacsight/kernel/retro"><img src="https://agentmods.dev/badge/commands/isaacsight/kernel/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/commands/isaacsight/kernel/retro"><img src="https://agentmods.dev/badge/commands/isaacsight/kernel/retro.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 440 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	$0.00000	$0.00440
Opus 5.5	$0.00000	$0.00176
Sonnet 5.5	$0.00000	$0.00088
Haiku 4.5	$0.00000	$0.00044

Measured 2mo ago against content hash 15be7a9e017f, 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 2mo 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.

.claude/commands/retro.md · 72 lines

What it actually says

Run a team retrospective. Agents review accumulated knowledge, prune stale entries, and identify tool gaps.

Protocol

1. Load All Memories

Read all agent memory files:

Call agent_memory_read for each: qa, designer, performance, security, devops, product
Also read shared-knowledge and tool-effectiveness

2. Analyze Patterns

For each agent's memory, identify:

Recurring issues — Problems that keep appearing (indicate systemic issues)
Stale entries — Findings that are no longer relevant (fixed issues, outdated metrics)
Wins — Successful patterns worth reinforcing
Gaps — Things agents needed but couldn't do

3. Prune Stale Entries

For each stale entry found:

Note what was stale and why
Suggest removal (but do NOT auto-delete — list for human review)

4. Identify Tool Gaps

Review tool-effectiveness.md for:

Tools with high failure rates
Agents that frequently work around missing capabilities
Propose new tools via create_tool if clear gaps emerge

5. Update Shared Knowledge

Call agent_memory_write for shared-knowledge with:

Key cross-cutting patterns discovered
Updated architecture decisions
Resolved coordination notes

6. Generate Retro Report

# Team Retrospective — [date]

## What's Working
[patterns and tools that consistently deliver value]

## Recurring Issues
[problems that keep appearing — need systemic fixes]

## Stale Entries (suggest pruning)
[entries that are no longer relevant, grouped by agent]

## Tool Effectiveness
| Tool | Uses | Success Rate | Notes |
|------|------|-------------|-------|

## Tool Gaps
[capabilities agents need but don't have]

## Proposed Tools
[new tools created via create_tool, if any]

## Action Items
1. [highest priority systemic fix]
2. [next priority]
...

7. Notify

Call kernel_notify on discord with retro summary.

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.

2mo ago First seen · 72 lines · 0 tokens per session scan A 15be7a9e017f

Subscribe to this mod's changes

retro is a command published in the GitHub repository isaacsight/kernel (16 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 440 tokens. 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 2026-09-03.

Building agents Project management agent-infrastructure ai-agent compliance-as-code eu-ai-act kbot mcp

retro next to 6 commands from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
retroisaacsight/kernel	Command	16	1mo ago	MIT	A	0	Claude Code
create-prdesplega-ai/agent-swarm	Command	1.0k	yesterday	MIT	A	19	Claude Code
riskreviewinclusionAI/Avernet	Command	601	yesterday	Apache-2.0	A	11	Claude Code
anchorsraccioly/docguard	Command	32	2d ago	MIT	A	11	Claude Code
initraccioly/docguard	Command	32	2d ago	MIT	A	9	Claude Code
briefraccioly/docguard	Command	32	2d ago	MIT	A	11	Claude Code
scriptwriter-opencambridgetcg/agenttool	Command	0	yesterday	Apache-2.0	A	47	Claude Code