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/agentic-development/adev-plugin/claude-mdgit clone --depth 1 https://github.com/agentic-development/adev-pluginWhat 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 | $0.02853 | $0.02853 |
| Opus 5 | $0.01426 | $0.01426 |
| Sonnet 5 | $0.00571 | $0.00571 |
| Haiku 4.5 | $0.00285 | $0.00285 |
Grade C, and why
adev-plugin CLAUDE.md scanned grade C with 2 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 2d 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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
<!-- Content below is preserved across syncs. Add Claude-specific instructions here. --> Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
1. **Minimize external dependencies** — prefer Node.js built-ins (`fs`, `path`, `child_process`, `crypto`, `node:test`). Justify any new dependency in an ADR. How it starts
The opening of the file, as written. The whole thing — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Identity
adev-plugin is a Claude Code plugin and zero-dependency CLI that implements a full-lifecycle Agentic Development Framework, providing markdown-based skills, bash hooks, and templates for scaffolding structured project context.
Non-Negotiable Principles
- Minimize external dependencies — prefer Node.js built-ins (
fs,path,child_process,crypto,node:test). Justify any new dependency in an ADR. - Skills are primarily markdown — skill files are structured instructions for Claude. Companion code (helpers, validators) is allowed but must not be required for the skill to function.
- Pure ESM — all
.mjsfiles,"type": "module"in package.json. No CommonJS. - Hook protocol compliance — hooks read JSON from stdin + env vars, exit 0 (allow) or 2 (block), output JSON to stdout.
- Version parity —
package.jsonand.claude-plugin/plugin.jsonversions must always match.
Coding Standards
Language and Runtime
- Primary language: JavaScript (ESM,
.mjsextension) - Runtime: Node.js
- Package manager: npm
Conventions
- Naming: camelCase for functions/variables, kebab-case for files and directories
- File structure: skills in
skills/<name>/SKILL.md, hooks inhooks/, templates intemplates/, CLI incli/ - Import ordering: Node.js built-ins first, then relative imports
- Error handling: hooks use exit codes (0 = allow, 2 = block); CLI uses
process.exit(1)for fatal errors - Logging: hooks output JSON to stdout; CLI uses
console.logfor user-facing output
Commit Trailers
Commits that implement or fix spec-tracked work must include a Spec: trailer linking back to the spec file. This enables /adev:retro and /adev:hygiene to trace commits to lifecycle artifacts.
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.
- 2d ago First seen · 181 lines · 2,853 tokens per session scan C 9e73f0959a29
adev-plugin CLAUDE.md is an instructions file published in the GitHub repository agentic-development/adev-plugin (11 stars, last pushed 2d ago), licensed MIT. It adds 2,853 tokens to every session, about $0.0143 per session on Opus 5. A static security scan graded it C with 2 findings (hidden instructions, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
buildNext
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
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, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit 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.
langchain 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.