What is local-workflow-skill CLAUDE.md?

Project instructions for a Markdown-based workflow framework and skill library used by several coding agents. It defines a process for restoring project state, choosing authority, doing the work, checking results, and recording progress.

Use it when doing substantial work in the repository, especially when you need to inspect framework guidance and update its state files.

It helps contributors follow a consistent workflow and keep requirements, memory, logs, and progress aligned with the repository.

How cass-2003/local-workflow-skill configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to cass-2003/local-workflow-skill. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/cass-2003/local-workflow-skill/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/cass-2003/local-workflow-skill

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/cass-2003/local-workflow-skill/claude-md/github.svg)](https://agentmods.dev/instructions/cass-2003/local-workflow-skill/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/cass-2003/local-workflow-skill/claude-md"><img src="https://agentmods.dev/badge/instructions/cass-2003/local-workflow-skill/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/cass-2003/local-workflow-skill/claude-md"><img src="https://agentmods.dev/badge/instructions/cass-2003/local-workflow-skill/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 857 This file is loaded in full into every session.

When invoked 857 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00857	$0.00857
Opus 5.5	$0.00343	$0.00343
Sonnet 5.5	$0.00171	$0.00171
Haiku 4.5	$0.00086	$0.00086

Measured 2mo ago against content hash 731cc42429b8, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

local-workflow-skill CLAUDE.md 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 2mo 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.md · 86 lines

How it starts

The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This repository is the source workspace for Portable Agent Workflow: a generic, Markdown-first workflow framework and curated skill library for multiple coding agents.

Claude Code should treat this file as a thin project entry. The workflow truth lives in framework/core/; repository state lives in state/.

Default Workflow

For substantial work, follow:

scan -> state restore -> intent -> authority -> route -> execute -> validate -> sync -> deliver -> evolve

Read:

framework/core/01-workflow.md
framework/core/02-state-systems.md
framework/core/03-routing.md
framework/core/04-authority.md
framework/core/05-validation.md
framework/core/06-evolution.md
framework/core/07-artifact-contracts.md
framework/core/08-autonomous-project-loop.md

Update state/LOG.md, state/REQUIREMENTS.md, state/MEMORY.md, and state/PROGRESS.md when repository truth changes.

Before substantial work, choose a Context Mode and produce a State Restore summary from the minimum sufficient sources: context capsule/latest progress, recent log entries, relevant memory/requirements sections, and changed files. Use full four-state reads only for first handoff, stale/conflicting state, high-risk workflow changes, or explicit broad audits. The summary must include context mode, state sources, stale/placeholders, latest goal, latest validation, blocker, and current assumptions. If placeholders or stale entries remain, replace what can be confirmed from repository facts before editing workflow behavior.

Artifact Contracts

Do not leave substantial audit, acceptance, implementation, fix, validation, or docs-sync work only in chat.

For audit / acceptance / 验收预检, create or update a report under docs/audit/ when the target project has that directory, and update docs/audit/INDEX.md.
For implementation or fixes, update the relevant state files, especially state/LOG.md and state/PROGRESS.md; update docs when behavior, usage, architecture, validation, or risk changes.
For docs changes, update docs/INDEX.md or the relevant directory index so new files are discoverable.
Before commit, confirm validation evidence, state sync, index sync, and git status; split multiple logical changes into multiple atomic commits.

Read the full file on GitHub · 86 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.

2mo ago First seen · 86 lines · 857 tokens per session scan A 731cc42429b8

Subscribe to this mod's changes

local-workflow-skill CLAUDE.md is an instructions file published in the GitHub repository cass-2003/local-workflow-skill (12 stars, last pushed 4mo ago), licensed MIT. It adds 857 tokens to every session, about $0.0034 per session on Opus 5.5. 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.

local-workflow-skill CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
local-workflow-skill CLAUDE.mdcass-2003/local-workflow-skill	Instructions file	12	4mo ago	MIT	A	857	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

local-workflow-skill: Instructions file for Claude Code