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.
npx agentmods add instructions/andreaserradev-gbj/dev-workflow/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.svg" alt="Measured on agentmods" 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 | $0.02782 | $0.02782 |
| Opus 5 | $0.01391 | $0.01391 |
| Sonnet 5 | $0.00556 | $0.00556 |
| Haiku 4.5 | $0.00278 | $0.00278 |
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 3d 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 — 225 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)
# 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.
- 3d 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 6d ago), licensed MIT. It adds 2,782 tokens to every session, about $0.0139 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.
Other instructions, from other repositories
gsd-core GEMINI.md
Gemini CLI instructions for open-gsd/gsd-core, covering gsd core — antigravity cli context, what gsd is, the slash commands (installed separately) and working with gsd.
personal-brain-builder AGENTS.md
Instructions for mikeshu2001/personal-brain-builder: When the user asks to start, resume, check, connect, or maintain their shared personal memory, read skills/build-personal-brain/SKILL.md completely and follow it.
personal-brain-builder CLAUDE.md
Instructions for mikeshu2001/personal-brain-builder: For requests to start, resume, check, connect, or maintain a shared personal memory, read skills/build-personal-brain/SKILL.md completely and follow it.
get-shit-done AGENTS.md
Instructions for gsd-build/get-shit-done, covering repository guidelines, active discussions, project structure & module organization, build, test, and development commands and coding style & naming conventions.
cat CLAUDE.md
Claude Code instructions for cowwoc/cat, covering project instructions, commit types for plugin files, plugin development and testing requirements.
wisci GEMINI.md
Gemini CLI instructions for ph3on1x/wisci: You have the WISCI skills available: /select, /write, /isolate, /compress, /commit.