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/alexsds/ade-workflow/claude-mdgit clone --depth 1 https://github.com/alexsds/ade-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/alexsds/ade-workflow/claude-md)<a href="https://agentmods.dev/instructions/alexsds/ade-workflow/claude-md"><img src="https://agentmods.dev/badge/instructions/alexsds/ade-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 | $0.00666 | $0.00666 |
| Opus 5 | $0.00333 | $0.00333 |
| Sonnet 5 | $0.00133 | $0.00133 |
| Haiku 4.5 | $0.00067 | $0.00067 |
Grade A, and why
ade-workflow CLAUDE.md scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- `testing-tools/playwright.md` — Browser-based UI testing (Playwright MCP, fallback to curl) How it starts
The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ADE — Agent-Driven Engineering
What This Is
A Claude Code plugin implementing Anthropic's 3-agent harness pattern (Planner, Generator, Evaluator) for long-running app development. Based on research from https://www.anthropic.com/engineering/harness-design-long-running-apps
Architecture
Skills are the source of truth for methodology. Agents are thin execution shells that reference skills. Commands are orchestration entry points.
skills/— methodology, knowledge, the "why" and "how" (single source of truth)agents/— execution shells that read skills for guidancecommands/— user-facing entry points that invoke agents
Development
This is a Claude Code plugin. Structure follows plugin-dev conventions:
.claude-plugin/plugin.json— manifestagents/— agent definitions (auto-discovered)commands/— slash commands (auto-discovered)skills/— skill directories with SKILL.md (auto-discovered)hooks/— event hooksscripts/— utility scriptsrubrics/— default evaluation rubrics (referenced by evaluator skill)testing-tools/— default testing tool configs (referenced by evaluator skill).mcp.json— Playwright MCP for browser-based evaluation
Key Principles
- Commands are instructions FOR Claude, not messages TO users
- Agent descriptions need
<example>blocks for reliable triggering - Use
${CLAUDE_PLUGIN_ROOT}for all internal paths, never hardcode - Rubrics and testing-tools are pluggable — defaults in plugin, overrides in .ade/
- Planner = subagent (interactive, one-shot). Generator + Evaluator = agent team (SendMessage)
- Skills hold the methodology, agents reference them — one place to update
Commit Style
Use conventional commits: feat:, fix:, docs:, chore:. Single-line messages.
Commands
scripts/init-project.sh # Initialize .ade/ in target project
scripts/validate-rubric.sh <f> # Validate rubric has required sections
scripts/validate-testing-tool.sh <f> # Validate testing tool definition
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 · 69 lines · 666 tokens per session scan A fe730ab19bd3
ade-workflow CLAUDE.md is an instructions file published in the GitHub repository alexsds/ade-workflow (1 stars, last pushed 5mo ago), licensed MIT. It adds 666 tokens to every session, about $0.0033 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
sd0x-harness CLAUDE.md
Claude Code instructions for sd0xdev/sd0x-harness, covering sd0x-dev-flow — harness engineering for claude code, required checks (stop hook reminded), auto-loop, development rules and footguns.
cc10x CLAUDE.md
Instructions for romiluz13/cc10x, covering cc10x orchestration (always on), complementary skills (work together with cc10x) and complementary skills (work together with cc10x).
ship-it open-pr.instructions.md
Instructions for khrichtchatyi/ship-it: When the user asks to open, create, or submit a pull request, follow the skill in skills/open-pr/SKILL.md in full: verify gh is authenticated, resolve the target repository and default branch, push the current branch, open one pull request with a title and body derived from the…
agent-skills CLAUDE.md
Instructions for mindbox-cloud/agent-skills, covering agent-skills — developer guide for claude code, repository purpose, repository structure, how to add a new plugin and step 1 — create the directory structure.
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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.