codebase-recon

A structured workflow for documenting an unfamiliar or poorly documented codebase in YAML files that coding agents can read.

In plain words
What is it for?
It helps map a repository, record its architecture and conventions, and create durable agent-readable project context.
Why use it?
It turns scattered project knowledge into a consistent format and avoids relying on outdated prose documentation.

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/prinova/pi-agent-codebase-workflows/codebase-recon
Any agent
npx skills add PriNova/pi-agent-codebase-workflows --skill codebase-recon
Clone the repo
git clone --depth 1 https://github.com/PriNova/pi-agent-codebase-workflows

Made for: Claude Code, Codex.

Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,122 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 $0.00035 $0.03122
Opus 5 $0.00017 $0.01561
Sonnet 5 $0.00007 $0.00624
Haiku 4.5 $0.00003 $0.00312

Measured 2d ago against content hash cde9c9420226, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

codebase-recon 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.

skills/codebase-recon/SKILL.md · 206 lines

How it starts

The opening of the file, as written. The whole thing — 206 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Codebase Reconstruction — Structured API Only

Goal: reconstruct durable project understanding into canonical YAML artifacts for coding-agent ingestion.

Structured Artifact API Contract

Legacy prose artifacts are deprecated. Do not create, update, or rely on docs/agent/*.md, scoped prose docs, or generated human-readable Markdown views. Use structured YAML for canonical artifacts. Root AGENTS.md remains a harness interoperability file and may be generated/updated only by workflows that explicitly say so.

Resolved structured docs root:

Treat docs/agent/api as a logical layout rooted at a resolved structured docs root, not a fixed repo path.

Resolution rules:

  1. Resolve workspace_root with git rev-parse --show-toplevel 2>/dev/null or fallback to pwd.
  2. Canonicalize workspace_root before fingerprinting when possible (realpath, pwd -P, Path(...).resolve(), or equivalent).
  3. safe-start always creates and uses the initial repo-local root: <workspace_root>/docs/agent/api.
  4. codebase-recon uses repo-local only when <workspace_root>/docs/agent/api already exists.
  5. Otherwise use the global overlay root: ~/.pi/agent/workspaces/<workspace-fingerprint>/docs/agent/api.
  6. Compute <workspace-fingerprint> exactly from canonical workspace_root: strip one leading slash/backslash, replace every slash, backslash, and colon with -, then wrap with --. This keeps the same workspace stable.
  7. Example: /data/data/com.termux/files/home/CodeProjects/pi-mono -> --data-data-com.termux-files-home-CodeProjects-pi-mono--.
  8. Do not create new repo-local structured docs in unadopted repos unless the user explicitly asks for repo-local adoption there.

Logical structured layout under the resolved docs root:

repo/
  scopes.yaml
  repo-inventory.yaml
  project-intent.yaml
  architecture.yaml
  data-flow.yaml
  data-model.yaml
  invariants.yaml
  dependency-rules.yaml
  design-issues.yaml
  risk-register.yaml
  change-guide.yaml
  testing-strategy.yaml
  validation-baseline.yaml
  contracts.yaml
  adr.yaml
  agent-operating-guide.yaml
scopes/
  by-path/<repo-relative-path>/...
  by-domain/<slug>/...

Read the full file on GitHub · 206 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. 2d ago First seen · 206 lines · 35 tokens per session scan A cde9c9420226

Subscribe to this mod's changes

codebase-recon is a skill published in the GitHub repository PriNova/pi-agent-codebase-workflows (82 stars, last pushed 2mo ago), licensed MIT. It adds 35 tokens to every session and 3,122 once invoked, about $0.0002 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 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens