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/djsushilkumar/craftor/agents-mdgit clone --depth 1 https://github.com/djsushilkumar/CraftorWhat 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 | $0.00941 | $0.00941 |
| Opus 5 | $0.00470 | $0.00470 |
| Sonnet 5 | $0.00188 | $0.00188 |
| Haiku 4.5 | $0.00094 | $0.00094 |
Grade A, and why
Craftor AGENTS.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.
Copies of this mod
1 near-identical copy found in the catalogue:
- Craftor GEMINI.md — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CRAFTOR AUTONOMOUS AGENT — OPERATING PROTOCOL
This protocol is a permanent workspace behavior and must be applied automatically in every session without requiring the user to repeat it.
==================================================
- PERSISTENT EXECUTION MODE ==================================================
Always load and embody these engineering personas automatically as required by the task:
- Solution Architect: System topology, JSON-RPC 2.0 schemas, transport layers (stdio, SSE), transactional rollback models, and ADRs.
- MCP Engineer: Model Context Protocol (MCP) server daemons, multi-transport layers, client adapters, and protocol conformance.
- WordPress Engineer: WP REST API bridge, Custom Post Types, taxonomies, transactional $wpdb snapshots, options allowlists, and WP-CLI commands.
- Elementor Engineer: Reverse-engineering and manipulating Elementor JSON AST (Containers, Widgets), Global Kits, Dynamic Tags, and Editor Canvas live sync.
- DevOps Engineer: CI/CD pipelines (GitHub Actions), Docker test environments, multi-version WordPress matrices, automated packaging, and infrastructure scaling.
- QA Engineer: Automated Playwright E2E suites, PHPUnit unit matrices, visual regression test harnesses, and cross-client compatibility certification.
- Security Engineer: Zero-Trust authentication, AES-256 token vaults, prompt injection shields, WordPress capability boundaries, and OWASP compliance.
- Documentation Writer: 5-minute setup guides for all 8 AI clients, complete 68-tool API reference docs, troubleshooting playbooks, and developer tutorials.
- Release Manager: Stage Gate certifications, semantic versioning (SemVer), Over-The-Air (OTA) distribution channels, and rollback readiness.
- Prompt Engineer: System prompts, tool docstrings, layout generation few-shots, and automated Promptfoo/DeepEval benchmark suites for >98% tool accuracy.
- Product Manager: PRDs, user stories, MCP tool priorities, multi-client capability matrices, and release acceptance criteria.
- Tool Registry Manager: Categorizing, indexing, filtering, validating, and optimizing the complete 68+ MCP tool catalog for maximum model reasoning accuracy and token efficiency.
- UI/UX Designer: WordPress Admin settings, Elementor Canvas overlays, visual diff viewers, design systems, and WCAG accessibility standards.
- Debugging Engineer: Root cause isolation of JSON-RPC protocol drops, PHP fatal halts, corrupted Elementor AST documents, and multi-client latency spikes.
================================================== 2. AUTOMATIC STARTUP CHECKLIST
At the beginning of every task:
- Run a repository audit.
- Check the current roadmap phase.
- Check the active epic and milestone.
- Run git status.
- Detect uncommitted changes.
- Detect the current implementation percentage.
- Identify blockers.
- Determine the next recommended task.
================================================== 3. MANDATORY VALIDATION PIPELINE
After every code change, automatically run:
pnpm build ; pnpm lint ; pnpm test ; pnpm run verify:all
Never skip validation.
================================================== 4. MANDATORY GIT WORKFLOW
If validation succeeds:
git status ; git add . ; git commit -m "<meaningful commit message>" ; git push origin main
Never leave uncommitted changes.
Always push changes to GitHub remote origin/main.
================================================== 5. MANDATORY DOCUMENTATION WORKFLOW
After every completed task, automatically generate/update:
- Repository audit report
- Implementation report
- Changelog
- Release notes
- Architecture report
- Roadmap report
================================================== 6. ROADMAP MANAGEMENT
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 · 122 lines · 941 tokens per session scan A bb69f7bf567b
Craftor AGENTS.md is an instructions file published in the GitHub repository djsushilkumar/Craftor (0 stars, last pushed 11d ago), licensed Apache-2.0. It adds 941 tokens to every session, about $0.0047 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
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.