pwp-docs

A process for keeping project documentation accurate, organized, and connected to the work that changes the code.

In plain words
What is it for?
Creating or updating documentation, recording plans and releases, and tracking why project changes were made.
Why use it?
It prevents README files, plans, architecture notes, and changelogs from becoming outdated or disconnected from implementation.

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/shandar/pwp-plugin/pwp-docs
Any agent
npx skills add shandar/pwp-plugin --skill pwp-docs
Clone the repo
git clone --depth 1 https://github.com/shandar/pwp-plugin

Made for: Claude Code, Codex.

Per session 112 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,196 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 $0.00112 $0.01196
Opus 5 $0.00056 $0.00598
Sonnet 5 $0.00022 $0.00239
Haiku 4.5 $0.00011 $0.00120

Measured 2d ago against content hash 504fd98e46ad, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

pwp-docs 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/pwp-docs/SKILL.md · 146 lines

How it starts

The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PWP Documentation Protocol

You are now operating under the Project Workflow Protocol's documentation discipline. Documentation is a living part of the codebase, not an afterthought.

Context: $ARGUMENTS

Phase 1: Identify Document Type

Determine which living document(s) need attention:

Document Purpose Update When
docs/VISION.md Product roadmap, feature IDs Adding/shipping features
docs/plans/README.md Plan registry & status Creating/completing plans
docs/plans/PLAN-*.md Implementation details During execution
CHANGELOG.md Version history Each release
docs/PRD.md Requirements Scope changes
docs/ARCHITECTURE.md Tech stack & diagrams System changes
README.md Project overview Setup/usage changes
CLAUDE.md AI agent instructions Pattern/convention changes

Phase 2: Feature Traceability

Use unique IDs to trace intent from vision to code:

Vision IDs:    A1, S1              (in VISION.md)
Plan IDs:      PLAN-001/P0         (in plan files)
Commits:       feat(PLAN-001/P0): description
Code Comments: // See PLAN-001/P2  (where non-obvious)

Traceability Chain

VISION.md (feature A1)
  → PLAN-003.md (implements A1)
    → commit: feat(PLAN-003/P1): add payment form
      → code comment: // See PLAN-003/P2 for validation rules

Every feature should be traceable from "why we're building it" to "where the code lives."

Phase 3: CHANGELOG Management

Follow Keep a Changelog format:

## [Unreleased]
### Added
- New payment processing module (PLAN-003)

### Changed
- Updated auth flow to support OAuth2 (PLAN-005)

### Fixed
- Cart total calculation rounding error (#142)

### Removed
- Legacy XML export endpoint (deprecated since v2.1)

Rules

  • Group by: Added, Changed, Deprecated, Removed, Fixed, Security
  • Reference plan IDs or issue numbers
  • Write for humans, not machines
  • Update with every meaningful PR, not just releases

Read the full file on GitHub · 146 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 · 146 lines · 112 tokens per session scan A 504fd98e46ad

Subscribe to this mod's changes

pwp-docs is a skill published in the GitHub repository shandar/pwp-plugin (1 stars, last pushed 6mo ago), licensed MIT. It adds 112 tokens to every session and 1,196 once invoked, about $0.0006 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.