Skip to content

cskwork/learn-codebase

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

2 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

learn-codebase

intent-anchored reading for codebases another agent built

A Claude Code skill (and a human technique) for understanding code another agent — human or AI — has written, by anchoring every read on its intent and reading both as paired columns.

Code without intent = ritual mimicry. Intent without code = aspiration. Side-by-side = bidirectional traceability you can act on.


What this skill does

It teaches you to read a feature in 4 progressive levels, stopping at the depth your task actually needs:

Level Budget Goal Artifact
1 — Map ≤5 min What is this & why does it exist? 3-line summary + one entry function
2 — Walk ≤30 min How does the happy path flow? Side-by-side trace table
3 — Probe ≤2 hr Why is it built this way? Decision matrix with rejected alternatives
4 — Master Deep What invariants hold it together? Invariant + seam map

Every artifact pairs an intent quote (from spec / ADR / contract / test) with the matching code (file:line) and a plain-language one-liner anyone outside the project can follow (the "Feynman" gate — see templates/plain-speech-checklist.md). If a cell is empty, that's a probe target — not a problem.

See SKILL.md for the full technique.


Why this exists

Three pain points this skill addresses:

  1. AI shipped a PR. You have a 100-file repo and a 40-page spec and need to review the diff. Top-down reading drowns; intent-anchored reading scales.
  2. Onboarding to one feature. You don't need the whole product — you need to grok this thing in 30 minutes. The skill gives a stopping rule.
  3. Spec ↔ code drift. Specs say X, code does Y, tests cover Z. The skill surfaces the gap explicitly via a drift diagnostic.

Install

As a Claude Code skill

# clone into your skills directory
git clone https://github.com/cskwork/learn-codebase \
  ~/.claude/skills/learn-codebase

Or symlink from a working directory you maintain:

git clone https://github.com/cskwork/learn-codebase ~/code/learn-codebase
ln -s ~/code/learn-codebase ~/.claude/skills/learn-codebase

Then in any Claude Code session, ask:

"Use learn-codebase to walk me through feature X."

Or invoke the skill explicitly with the Skill tool when the agent asks how to proceed.

As a human technique (no Claude Code required)

Read SKILL.md. Open templates/sidebyside.md. Follow the 4 levels. Stop when your task is done.


Repository layout

learn-codebase/
├── SKILL.md                                  # The skill itself (the main read)
├── README.md                                 # You are here
├── LICENSE
├── templates/
│   ├── plain-speech-checklist.md             # Mandatory Feynman-style output gate
│   ├── sidebyside.md                         # The walk-table format
│   └── progression-checklist.md              # Per-level checklist
├── examples/
│   └── twin-question-platform.md             # Levels 1-3 applied to a real spec
└── references/
    ├── finding-intent.md                     # Where to look first (forward + reverse direction)
    └── diagnostic.md                         # Intent ↔ code drift self-audit

Use cases

  • Joining an AI-assisted team mid-stream.
  • Reviewing AI-generated PRs against a written spec.
  • Teaching a junior dev one feature without overwhelming them.
  • Planning a refactor: knowing every test that will turn red before you change anything.
  • Recovering intent from code when documentation has lapsed (Reverse direction).

Acknowledgements

The skill builds on patterns from:

  • Domain-Driven Design — ubiquitous language and bounded contexts.
  • Literate programming — code paired with prose.
  • Requirements traceability (IBM DOORS lineage) — bidirectional mapping.
  • Test-driven development — tests as executable intent.
  • Anthropic's skill-authoring guide (writing-skills) — TDD applied to documentation.

License

MIT. See LICENSE.


Contributing

Issues and PRs welcome. If the skill fails on a real codebase you tried it on, that's the highest-value bug report — open an issue with:

  • the project type (mono-repo / split planning + code / etc.),
  • which level you got stuck at,
  • the missing piece in the skill or templates.

The skill's quality is measured by whether a fresh agent can apply it to a new codebase without prior context. Reports of failure on real codebases make the skill better.

About

Intent-anchored reading skill - learn a codebase another agent built, with a Feynman/plain-speech gate on every output.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors