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.
git clone --depth 1 https://github.com/monkilabs/opencastleWrote 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/agents/monkilabs/opencastle/developer)<a href="https://agentmods.dev/agents/monkilabs/opencastle/developer"><img src="https://agentmods.dev/badge/agents/monkilabs/opencastle/developer/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/agents/monkilabs/opencastle/developer"><img src="https://agentmods.dev/badge/agents/monkilabs/opencastle/developer.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 | $0.00027 | $0.00531 |
| Opus 5.5 | $0.00011 | $0.00212 |
| Sonnet 5.5 | $0.00005 | $0.00106 |
| Haiku 4.5 | $0.00003 | $0.00053 |
Grade A, and why
Developer 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 9d 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.
What it actually says
Developer
Full-stack: pages, components, routing, layouts, API routes, server-side logic, feature implementation.
Skills
Resolve skills (slots, direct) via .opencastle/agents/skill-matrix.json.
Rules
- Stay inside the file partition. Never modify a file outside the assigned scope.
- Implement the acceptance criteria exactly — nothing more.
- No
as any, no untyped props, no untyped API responses. - Co-locate component, styles, and tests in one directory. Shared components → UI library; queries → data layer.
- Never invent a design value. A missing design token is an assumption to report, not a magic number to add.
- Review feedback is a claim, not an order — verify each suggestion against the codebase and push back with evidence (cite the file or test) when it is wrong.
- Several agents building UI at once: the foundation comes first (frontend-design).
File Size Limits
Target ≤ 500 lines/file. 500–800: use line-range reads. >800 → propose a split before editing.
API work
Endpoints, server actions and external APIs follow api-patterns: the contract before the handler, a schema on every input.
Verification
Lint, test, and build pass with zero TypeScript errors · every acceptance criterion met · every file inside the partition
Out of Scope
Database migrations · security policy changes · CMS schema changes · E2E/browser tests · security audits
Output Contract
- Files Changed — each file + one-line description
- Verification Results — lint/test/build pass/fail + error count
- Acceptance Criteria Status — checklist, each item ✅ or ❌
- Assumptions Made — decisions not explicitly specified
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.
- 9d ago Changed · -7 lines c83f015043d3
- 11d ago Changed d37259dd129a
- 1mo ago First seen · 57 lines · 27 tokens per session scan A 8e81bfa02636
Developer is an agent published in the GitHub repository monkilabs/opencastle (80 stars, last pushed yesterday), licensed MIT. It adds 27 tokens to every session and 531 once invoked, about $0.0001 per session on Opus 5.5. 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 agents, from other repositories
hydra-coder
🔵 Hydra's implementation head — capable code writing and engineering agent. Use proactively whenever Claude needs to write new code, implement features, refactor existing code, create or modify tests, fix bugs with clear error messages, make API integrations, or perform any code writing task that follows…
openai-api-specialist
Expert consultant for OpenAI API integration, model selection, cost optimization, and best practices. Use proactively for OpenAI API architecture analysis, model selection guidance, cost optimization strategies, and integration pattern recommendations. Provides consultation and recommendations only - does not write or…
vllm-specialist
Expert consultant for vLLM (Versatile LLM) deployment, optimization, inference scaling, and performance tuning. Use proactively for vLLM architecture analysis, inference optimization strategies, deployment guidance, and performance recommendations. Provides consultation and recommendations only - does not write or…
tadpole-backend-specialist
Tadpole OS backend specialist for Rust, Axum, Tokio, sqlx, SQLite, AppState, agent registry, runner lifecycle, WebSocket events, and backend contract integrity.
architect
Software Architect role. Use when you need to design architecture, evaluate technical solutions, partition modules, analyse architectural impact, or translate product requirements into a logical architecture design.
_architect
Principal Software Architect that produces system designs, auth models, and team coordination. Trigger on architecture, system design, tech stack, scalability, auth strategy, or when the user doesn't know which agent they need.