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/amethystluna/embedded-workbench/claude-mdgit clone --depth 1 https://github.com/AmethystLuna/embedded-workbenchWhat 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 | $0.01240 | $0.01240 |
| Opus 5 | $0.00620 | $0.00620 |
| Sonnet 5 | $0.00248 | $0.00248 |
| Haiku 4.5 | $0.00124 | $0.00124 |
Grade A, and why
embedded-workbench 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 yesterday.
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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Contributor guidelines for the Embedded Engineering Workflow plugin.
Acknowledgments
This plugin's agent-compliance architecture (1% Rule, Red Flags, <SUBAGENT-STOP>, instruction priority, skill types, session-start hook injection) is adapted from Superpowers by Jesse Vincent (MIT License). The trigger test framework structure (tests/skill-triggering/) follows Superpowers' testing conventions.
PR Requirements
- All PRs must pass
markdownlintwith the project's.markdownlint.jsonconfig. - New skills must follow the established frontmatter format:
name(kebab-case),description("Use when..." format). - Agent changes must maintain the tool allowlist (
toolsfield):- Read-only agents (
architecture-steward,quality-coordinator) must not gain Write or Edit. - Review agents (
design-reviewer) may include Bash for read-only verification (grep, markdownlint, build checks) — add explicit "Bash for verification only" guidance in the agent prompt. - Implementation agents (
execution-worker) require Write + Edit + Bash.
- Read-only agents (
- Skill content must not hardcode project-specific details (file paths, version numbers, product names).
- Chinese content should have English equivalents in the bootstrap skill and vice versa.
Before Submitting
- Run
markdownlinton all changed files. - Verify
plugin.jsonpassesclaude plugin validate. - Test the plugin locally by installing to
~/.claude/plugins/dev/. - Bump the version with the release tool:
npm run bump -- <new-version>(syncs every declared manifest —package.json,package-lock.json×2, all plugin manifests,.version-bump.json— plusDSH-COMPATIBILITY.md;npm run bump -- --checkandnpm run bump -- --auditmust pass).
CI Workflows (GitHub Actions)
dsh-bundle— on push/PR touchingsrc/,lib/,cordis.patch.yml,package.json,package-lock.json, docs, or the workflow itself:npm ci --legacy-peer-deps, typecheck, build, committed-lib/drift guard, and markdownlint on.dsh/**/*.md, READMEs, andRELEASE.md.Plugin Security Scan— on every push/PR:hashgraph-online/ai-plugin-scanner-actionon the repo root; fails on high-severity findings.
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.
- yesterday First seen · 89 lines · 1,240 tokens per session scan A 1f914834de86
embedded-workbench CLAUDE.md is an instructions file published in the GitHub repository AmethystLuna/embedded-workbench (5 stars, last pushed yesterday), licensed MIT. It adds 1,240 tokens to every session, about $0.0062 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
deepseek-harness AGENTS.md
Instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-release stance: foundation over blast radius, repository layout, commands and host sandbox failures.
deepseek-harness CLAUDE.md
Instructions for deepseek-ai/deepseek-harness, a project described as: DeepSeek Harness: Everything is a Plugin.
dsh-web AGENTS.md
Instructions for zhu1090093659/dsh-web, covering dsh-web repository instructions, repository layout, common commands, repository rules and development workflow.
better-harness AGENTS.md
Instructions for QoderAI/better-harness, covering better harness, ui and visual design, plan & spec, change scope and host adapters.
modsearch AGENTS.md
Instructions for liustack/modsearch, covering project overview (for ai agent), goal, technical approach, code organization and skills directory.
acryl AGENTS.md
Instructions for acryldev/acryl, covering dsh desktop repository rules, prerequisites and setup, build, run, and verify, cordis development protocol and agent skills.