capture-lessons

capture-lessons is a skill for Claude Code, Codex from rbah31/claude-code-workflow. It costs 100 tokens per session (2,245 once invoked), scanned A, original, Apache-2.0.

A workflow for closing a software sprint, a planned period of development work. It prepares the code for delivery, records lessons, updates documentation and the backlog, and creates a retrospective, which is a review of what happened.

In plain words
What is it for?
Use it when a sprint is finished or when you need to ship work, capture lessons, update docs, prepare a retrospective, and refresh the backlog.
Why use it?
It keeps the end of a sprint from being reduced to merging code while important notes, documentation, and follow-up work are forgotten.

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/rbah31/claude-code-workflow/capture-lessons
Any agent
npx skills add rbah31/claude-code-workflow --skill capture-lessons
Clone the repo
git clone --depth 1 https://github.com/rbah31/claude-code-workflow

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 capture-lessons

README.md
[![agentmods](https://agentmods.dev/badge/skills/rbah31/claude-code-workflow/capture-lessons.svg)](https://agentmods.dev/skills/rbah31/claude-code-workflow/capture-lessons)
Your own site
<a href="https://agentmods.dev/skills/rbah31/claude-code-workflow/capture-lessons"><img src="https://agentmods.dev/badge/skills/rbah31/claude-code-workflow/capture-lessons.svg" alt="Measured on agentmods" height="20"></a>
Per session 100 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,245 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 $0.00100 $0.02245
Opus 5 $0.00050 $0.01123
Sonnet 5 $0.00020 $0.00449
Haiku 4.5 $0.00010 $0.00225

Measured 4d ago against content hash e12adbfe3ba2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

capture-lessons 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 4d 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/skills/capture-lessons/SKILL.md · 252 lines

How it starts

The opening of the file, as written. The whole thing — 252 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ship & Capture Phase

You are running the final phase of the sprint. Your job is to close the loop: ship the code, capture what was learned, and prepare for the next sprint.

Step 1 — Load context

First, determine the current sprint: look at tasks/sprints/ directories and find the most recent one (highest number). Call it sprint-XX below.

Read all sprint artifacts:

  1. tasks/sprints/sprint-XX/plan.md — what was planned
  2. tasks/sprints/sprint-XX/build-output.md — what was built
  3. tasks/sprints/sprint-XX/review-output.md — what was found in review
  4. tasks/sprints/sprint-XX/fix-output.md — what was fixed
  5. tasks/sprints/sprint-XX/redteam-output.md — security findings (if exists, skip if not)
  6. tasks/lessons.md — existing lessons

If any artifact is missing (e.g., no red-team output for a normal sprint), note its absence and continue with what's available.

Step 2 — Create the PR

Prepare a pull request description based on the sprint artifacts:

## Sprint XX — [Theme]

### What changed
[Summary of changes from build-output]

### Key decisions
[Technical decisions and their rationale]

### Testing
[Tests added, coverage changes]

### Security
[Security considerations, red team findings if applicable]

### Review notes
[Anything the PR reviewer should know]

If git is configured, create the PR. Otherwise, save the PR description to tasks/sprints/sprint-XX/pr-description.md for the human to use.

Step 3 — Update lessons learned

Add new entries to tasks/lessons.md based on what happened this sprint.

Each lesson follows this format:

### [Date] — [Author or "Claude"] — Sprint XX
**Context**: [What was happening]
**What went wrong (or right)**: [What happened]
**Lesson**: [The takeaway — a rule to follow going forward]

Look for lessons in:

  • Review findings that were critical (why weren't they caught earlier?)
  • Fix output (any recurring patterns?)
  • Red team findings (any systemic security issues?)
  • Build blockers (what slowed us down?)
  • Things that went well (what should we keep doing?)

Read the full file on GitHub · 252 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. 4d ago First seen · 252 lines · 100 tokens per session scan A e12adbfe3ba2

Subscribe to this mod's changes

capture-lessons is a skill published in the GitHub repository rbah31/claude-code-workflow (5 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 100 tokens to every session and 2,245 once invoked, about $0.0005 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

task-final-report

Apply the final report and PR publication procedure for a Hyper-Waterfall task. Write the final report (report.md), mark the daily task board complete, create the final commit, push the remote publish/task{N} branch, and create an Open PR to {BASEBRANCH}. Invoke only immediately before PR publication after all stages…

postmelee/hyper-waterfall · 74 tokens

batch

Research and plan a large-scale change, then execute it in parallel across 5–30 isolated worktree agents that each open a PR.

asgeirtj/system_prompts_leaks · 30 tokens

tutti-app-release

Set up, review, run, or debug external repositories that publish a Tutti workspace app through the reusable Tutti App Release GitHub Actions workflow. Use for caller workflows, tutti.app.json manifests, @tutti-os/app-release-tools, S3/CloudFront release hosting, latest.json, versions.json, catalog.json, catalog-only…

tutti-os/tutti · 80 tokens

moai-kanban-foreman

One unattended kanban foreman iteration: watch the backlog queue, dispatch the next operator-picked card to an isolated worker, collect completion evidence on read (not on claims), and report. This is the body the project's loop.md driver invokes each iteration of a bare /loop; it can also be invoked directly to test…

modu-ai/moai-adk · 76 tokens

moai-workflow-project

Integrated project management system covering documentation, language initialization, template optimization, docs generation, and JIT document loading. Absorbed from moai-workflow-templates, moai-docs-generation, and moai-workflow-jit-docs.

modu-ai/moai-adk · 55 tokens

close-task-commit-push-pr

Close the active backlog task (detected from branch name), commit all changes, push to remote, and open a pull request. Use when the user says "close task and ship it", "close task commit push pr", or invokes /close-task-commit-push-pr.

devoxx/DevoxxGenieIDEAPlugin · 64 tokens