Borrowing it
Nothing to install: this file belongs to andreaserradev-gbj/dev-workflow. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/andreaserradev-gbj/dev-workflow/main/CLAUDE.mdgit clone --depth 1 https://github.com/andreaserradev-gbj/dev-workflowWrote 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.
[](https://agentmods.dev/instructions/andreaserradev-gbj/dev-workflow/claude-md)<a href="https://agentmods.dev/instructions/andreaserradev-gbj/dev-workflow/claude-md"><img src="https://agentmods.dev/badge/instructions/andreaserradev-gbj/dev-workflow/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.
<a href="https://agentmods.dev/instructions/andreaserradev-gbj/dev-workflow/claude-md"><img src="https://agentmods.dev/badge/instructions/andreaserradev-gbj/dev-workflow/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.02808 | $0.02808 |
| Opus 5.5 | $0.01123 | $0.01123 |
| Sonnet 5.5 | $0.00562 | $0.00562 |
| Haiku 4.5 | $0.00281 | $0.00281 |
Grade A, and why
dev-workflow 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 17d 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.
How it starts
The opening of the file, as written. The whole thing — 228 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Project Overview
Claude Code plugin for multi-session development workflows. See README.md for usage and installation.
Repository Structure
plugins/dev-workflow/ # Plugin package
.claude-plugin/
plugin.json # Plugin metadata (includes agents array)
skills/ # Self-contained skills (AgentSkills.io format)
dev-plan/
SKILL.md
references/prd-templates.md
scripts/discover.sh, validate.sh, dev-workflow.cjs
agents/prd-researcher.md, prd-planner.md
dev-checkpoint/
SKILL.md
references/checkpoint-template.md, worktree-guide.md
scripts/discover.sh, validate.sh, git-state.sh, worktree-setup.sh, dev-workflow.cjs
dev-review/
SKILL.md
scripts/discover.sh, validate.sh, git-state.sh, dev-workflow.cjs
agents/feature-reporter.md
dev-resume/
SKILL.md
scripts/discover.sh, validate.sh, git-state.sh, dev-workflow.cjs
dev-wrapup/
SKILL.md
scripts/discover.sh
dev-wiki/
SKILL.md
scripts/discover.sh, validate.sh, dev-workflow.cjs
dev-dashboard/
SKILL.md
scripts/start.sh, stop.sh, read-port.cjs
dashboard/ # Bundled server + client (committed build artifact)
server/index.cjs
client/
dev-dashboard-tui/
SKILL.md
scripts/launch.sh # Foreground `exec node` launcher (user-run)
tui/cli.mjs # Bundled Ink TUI (committed build artifact, ESM)
dev-orchestrator/
SKILL.md
scripts/discover.sh, validate.sh, dev-workflow.cjs
# Generated in user's project (not in plugin repo)
.dev/wrapup-feedback.json # Wrapup feedback history (auto-compacting)
.codex/
INSTALL.md # Installation instructions for Codex
docs/
README.codex.md # Codex usage documentation
.claude-plugin/
marketplace.json # Marketplace metadata
.githooks/ # Git hooks (activate with scripts/setup.sh)
pre-commit # Runs tests before commit
pre-push # Enforces version bumps
tools/dev-dashboard/ # Cross-project live dashboard (web)
bin/dev-dashboard # Shell entry point
src/server/ # Fastify backend (scanner, parser, watcher, API, WS)
src/client/ # Preact frontend (portfolio view, detail panels)
src/shared/ # Shared TypeScript types
test/ # Vitest tests + fixtures
tools/dev-dashboard-tui/ # Cross-project dashboard, terminal-native (Ink TUI)
src/ # Ink components, hooks (useStore/useNavigation), theme
scripts/bundle.js # esbuild-bundles the TUI to the skill's tui/cli.mjs (ESM)
test/ # Vitest + ink-testing-library
tools/dev-workflow-core/ # Shared workflow core (parser, scanner, types)
src/ # TypeScript source
test/ # Vitest tests + fixtures
tools/dev-workflow-cli/ # Agent-first CLI over the shared core
src/commands/ # CLI commands (feature-show, progress-summary, etc.)
test/ # Vitest tests
scripts/bundle.js # Bundles CLI to plugins/dev-workflow/bin/dev-workflow.cjs
plugins/dev-workflow/bin/
dev-workflow.cjs # Bundled CLI artifact (canonical copy)
scripts/
setup.sh # One-time contributor setup
tests/
test-scripts.sh # Script edge-case tests + cross-skill sync checks
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.
- 17d ago Changed · +3 lines · +26 tokens per session 0e5cf0777d8a
- 2mo ago First seen · 225 lines · 2,782 tokens per session scan A 6bc90e62b497
dev-workflow CLAUDE.md is an instructions file published in the GitHub repository andreaserradev-gbj/dev-workflow (2 stars, last pushed 9d ago), licensed MIT. It adds 2,808 tokens to every session, about $0.0112 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 2026-08-31.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.