retro

retro is a skill for Claude Code, Codex from lisihao/Solar. It costs 15 tokens per session (323 once invoked), scanned A, original, MIT.

A sprint-retrospective workflow that reviews what went well, identifies root causes of failures, records lessons, and updates project state files. A sprint retrospective is a review held after a development cycle to improve the next one.

In plain words
What is it for?
Use it to review evaluation results, extract practical rules, update STATE.md, and record lessons in the project knowledge store.
Why use it?
It helps teams learn from failed checks instead of only recording symptoms. It leaves the lessons and next actions in the project’s shared records.

Skill for Claude CodeCodex

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/lisihao/solar/retro
Any agent
npx skills add lisihao/Solar --skill retro
Clone the repo
git clone --depth 1 https://github.com/lisihao/Solar

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 retro

README.md
[![agentmods](https://agentmods.dev/badge/skills/lisihao/solar/retro.svg)](https://agentmods.dev/skills/lisihao/solar/retro)
Your own site
<a href="https://agentmods.dev/skills/lisihao/solar/retro"><img src="https://agentmods.dev/badge/skills/lisihao/solar/retro.svg" alt="Measured on agentmods" height="20"></a>
Per session 15 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 323 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 $0.00015 $0.00323
Opus 5 $0.00008 $0.00161
Sonnet 5 $0.00003 $0.00065
Haiku 4.5 $0.00002 $0.00032

Measured yesterday against content hash 80e2adf91c4c, 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 yesterday.

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.

harness/skills/builtins/retro/SKILL.md · 50 lines

What it actually says

Skill: retro

Post-sprint retrospective: what worked, what failed, lessons extracted, STATE.md updated.

Trigger

User says: 回顾, 复盘, retro, /retro

Steps

  1. Read eval.md — review all PASS/FAIL items from the sprint evaluator
  2. What worked — list 2-3 things that went well
  3. What failed — list FAIL items with root-cause (not symptoms)
  4. Lessons — actionable rules extracted from failures
  5. Update STATE.md — add to Progress.Done + Next Actions if needed
  6. Write cortex — INSERT INTO cortex_sources for each lesson (credibility ≥ 0.8)
  7. Write sys_favorites — if insight score ≥ 7

Output format

## Worked
- ...

## Failed
- [item]: root-cause

## Lessons Extracted
1. [rule]: why it matters

## Cortex entries written: N
## STATE.md updated: yes/no

Done when

All FAIL items have root-causes, ≥1 cortex entry written, STATE.md updated.

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. yesterday First seen · 50 lines · 15 tokens per session scan A 80e2adf91c4c

Subscribe to this mod's changes

retro is a skill published in the GitHub repository lisihao/Solar (2 stars, last pushed 22d ago), licensed MIT. It adds 15 tokens to every session and 323 once invoked, about $0.0001 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 2026-09-03.

Related

Other skills, from other repositories

cocoreview

CocoReview — structured code review with six-severity findings vocabulary, progressive disclosure architecture, and universal anti-pattern baseline. Invoked via $review [file] [--complexity] [--security] [--architecture] [--language ].

Snowflake-Labs/cocoplus · 57 tokens

pod-init

Initialize CocoPlus project bundle in the current directory. Creates .cocoplus/ directory structure, copies all templates, initializes AGENTS.md, project.md, flow.json, and creates the initial git commit. Run this once per project before using any other CocoPlus command.

Snowflake-Labs/cocoplus · 57 tokens

spec

Enter the Spec phase of CocoBrew. Guides the developer through structured requirements capture: goal, success criteria, constraints, personas involved, data sources, and deliverables. Writes spec.md to .cocoplus/lifecycle/ and creates a git commit.

Snowflake-Labs/cocoplus · 53 tokens

discuss

Run a structured decision-capture dialogue before $plan — locks implementation choices (model, evaluation methodology, accuracy threshold, scope boundaries) into discuss.md to prevent silent decision drift during planning. Supports --red-team flag for adversarial post-PASS challenge session.

Snowflake-Labs/cocoplus · 54 tokens

cocoharvest

Decompose an approved plan into parallel workstreams, assign specialist personas, classify stages as HITL or AFK (CocoLens), generate flow.json stages with checkpoints and dual-file state, and create per-stage prompt files. Includes adaptive parallelism, stall detection, shell identity injection, and consecutive…

Snowflake-Labs/cocoplus · 68 tokens

pull

Distill large context files (evaluation artifacts, schema dumps, query result sets, analysis outputs) into LLM-optimized dense form or human-readable narrative (--human). Default output is machine-dense; --human produces a prose summary for stakeholder consumption.

Snowflake-Labs/cocoplus · 52 tokens