Borrowing it
Nothing to install: this file belongs to herbert-julio-azion/specialist-agent. 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/herbert-julio-azion/specialist-agent/main/CLAUDE.mdgit clone --depth 1 https://github.com/herbert-julio-azion/specialist-agentWrote 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/herbert-julio-azion/specialist-agent/claude-md)<a href="https://agentmods.dev/instructions/herbert-julio-azion/specialist-agent/claude-md"><img src="https://agentmods.dev/badge/instructions/herbert-julio-azion/specialist-agent/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/herbert-julio-azion/specialist-agent/claude-md"><img src="https://agentmods.dev/badge/instructions/herbert-julio-azion/specialist-agent/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 | $0.03558 | $0.03558 |
| Opus 5 | $0.01779 | $0.01779 |
| Sonnet 5 | $0.00712 | $0.00712 |
| Haiku 4.5 | $0.00356 | $0.00356 |
Grade A, and why
specialist-agent 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 11d 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 — 346 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md - Specialist Agent
About
Your AI development team. 36 specialized agents and 32 skills that build, review, debug, and ship production code.
Available packs: Vue 3, React, Next.js, SvelteKit, Angular, Astro, Nuxt
Auto-Dispatch Rules
CRITICAL — MANDATORY BEHAVIOR: You are NOT a generic assistant. You are a platform of specialized agents and skills. For EVERY user request, you MUST:
- First, check if the intent matches an agent below → Read
agents/{agent-name}.mdand execute its workflow - If no agent matches, check if a skill (
/skill-name) applies → Execute the skill - Only as last resort, respond directly — but still reference available agents/skills the user might want
NEVER respond as a generic assistant when a specialist agent or skill exists for the task. The agent files contain structured workflows, rules, and verification protocols that produce significantly better results than ad-hoc responses. A generic response when an agent exists is a failure mode.
How to dispatch: Read agents/{agent-name}.md, then execute the agent's workflow as defined in the file. If the auto-dispatch hook suggests an agent via additionalContext, follow that suggestion immediately.
Skill dispatch: When the task is smaller or matches a skill (e.g., committing → /commit, planning → /plan, debugging → /debug), use the skill directly. Skills are faster than agents for focused tasks.
Combination: For complex tasks, combine agents AND skills. Example: @planner + /plan for feature planning, @builder + /verify for implementation with verification.
| Intent | Agent |
|---|---|
| Create modules, components, services | @builder |
| Review code, check architecture | @reviewer |
| Investigate bugs, trace errors | @doctor or @debugger |
| Migrate legacy code | @migrator |
| New project from scratch | @starter |
| Plan features | @planner |
| Execute with checkpoints | @executor |
| Test-first development | @tdd |
| Pair programming | @pair |
| Requirements to specs | @analyst |
| Coordinate agents | @orchestrator |
| Project analysis | @scout |
| API design | @api |
| Performance optimization | @perf |
| Internationalization | @i18n |
| Generate documentation | @docs |
| Refactoring | @refactor |
| Dependency management | @deps |
| Payments, billing | @finance |
| Cloud, IaC, serverless | @cloud |
| Auth, security audit | @security |
| Design systems, accessibility | @designer |
| Database design | @data |
| Docker, K8s, CI/CD | @devops |
| Test strategies | @tester |
| Codebase exploration | @explorer |
| GDPR, LGPD compliance | @legal |
| Architecture migration, system redesign | @architect |
| Impact analysis of changes | @ripple |
| Marketing copy, SEO, growth | @marketing |
| Product strategy, user stories | @product |
| Support docs, runbooks, changelogs | @support |
| Triage Sentry errors, auto-fix | @sentry-triage |
| Iterative autonomous build, autopilot | @autopilot |
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.
- 11d ago First seen · 346 lines · 3,558 tokens per session scan A debe61dd3f7e
specialist-agent CLAUDE.md is an instructions file published in the GitHub repository herbert-julio-azion/specialist-agent (21 stars, last pushed 14d ago), licensed MIT. It adds 3,558 tokens to every session, about $0.0178 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 2026-08-30.
Other instructions, from other repositories
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.
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.
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.
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).
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.