retro

A structured end-of-session review that examines recent Git changes and proposes improvements to rules or documentation.

In plain words
What is it for?
Summarizing the session, recording struggles, analyzing missing rules or documentation, and suggesting specific file changes without applying them.
Why use it?
It helps identify what went wrong, why time was lost, and which shared files could prevent similar problems.

Command for Claude Code

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 commands/gosha70/code-copilot-team/retro
Clone the repo
git clone --depth 1 https://github.com/gosha70/code-copilot-team

Made for: Claude Code.

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 389 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 $0.00000 $0.00389
Opus 5 $0.00000 $0.00195
Sonnet 5 $0.00000 $0.00078
Haiku 4.5 $0.00000 $0.00039

Measured 2d ago against content hash d9efd7bf89f2, 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 2d 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.

adapters/claude-code/.claude/commands/retro.md · 50 lines

What it actually says

Post-Session Retrospective

Run a structured retrospective for the current session. Proposes rule and documentation changes but does not apply them.

Steps

1. Session Summary

  • Run git log --oneline -20 and git diff --stat to see what changed
  • Summarize: what was the goal? What was delivered?
  • Note any gap between intent and outcome

2. Struggle Identification

Build a table of struggles encountered during this session:

Struggle Time Lost Root Cause Category
{description} {estimate} {what was missing or wrong} {underspec / tooling / convention / context loss}

Categories:

  • underspec — requirement was ambiguous or incomplete
  • tooling — tool limitation or misconfiguration
  • convention — rule missing or unclear
  • context loss — agent forgot or lost track of earlier decisions

3. Rule/Doc Gap Analysis

For each struggle, propose a specific fix:

Struggle Proposed Fix Target File
{from table above} {concrete change} {path in shared/skills/, shared/templates/, or adapters/}

Be specific: "Add rule X to file Y" not "improve documentation."

4. What Worked Well

  • List patterns, rules, or workflows that prevented problems
  • Identify agent configurations that were effective
  • Note any conventions that saved time

5. Output

Write the retrospective to doc_internal/retro-{YYYY-MM-DD}.md (ask the user before writing).

Include all 4 sections above plus a summary of proposed changes.

Important: This command proposes rule changes but does not apply them. The user decides which proposals to implement.

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. 2d ago First seen · 50 lines · 0 tokens per session scan A d9efd7bf89f2

Subscribe to this mod's changes

retro is a command published in the GitHub repository gosha70/code-copilot-team (6 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 389 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 2026-08-31.