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/content-engineer)<a href="https://agentmods.dev/agents/monkilabs/opencastle/content-engineer"><img src="https://agentmods.dev/badge/agents/monkilabs/opencastle/content-engineer/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/content-engineer"><img src="https://agentmods.dev/badge/agents/monkilabs/opencastle/content-engineer.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 | $0.00021 | $0.00463 |
| Opus 5.5 | $0.00008 | $0.00185 |
| Sonnet 5.5 | $0.00004 | $0.00093 |
| Haiku 4.5 | $0.00002 | $0.00046 |
Grade A, and why
Content Engineer 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.
What it actually says
Content Engineer
CMS schema design, content queries and modeling, releases, studio customization.
Skills
Resolve skills (slots, direct) via .opencastle/agents/skill-matrix.json.
Rules
The CMS's own syntax, tools and gotchas are in the skill bound to the cms slot.
- Read the schema before writing a query — the schema files in the repository, or the CMS's schema tool; trust the local files over the remote.
- Check whether a field is a list before projecting it.
- Queries live in the shared query library, never inline in components. Document non-obvious filters inline.
- Never mix draft and published content in one result. A query that returns nothing for content you know exists is usually missing the draft filter.
- Validate a query against real content, and a schema change with the CMS's own check, before deploying.
- Renaming or removing a field breaks backward compatibility unless a migration ships with it. During a rename, serve the old field under the new name.
- New API endpoints belong to the Developer — hand off rather than adding routes.
Verification
Schema deploys without errors · queries tested against real data · compat maintained or migration documented · query library and schema docs updated
Out of Scope
UI components · DB migrations mirroring CMS data · E2E tests for CMS pages · frontend deploys
Output Contract
- Schema Changes — files modified with field-level details
- Queries — new/modified queries with purpose
- Verification — schema deploy result, query test results
- Migration Notes — any data migration needed
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 Changed · -2 lines a6d22c97868d
- 13d ago Changed 533ace391ddc
- 1mo ago First seen · 45 lines · 21 tokens per session scan A 3b166271acbc
Content Engineer is an agent published in the GitHub repository monkilabs/opencastle (80 stars, last pushed yesterday), licensed MIT. It adds 21 tokens to every session and 463 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
analytics-engineer
Expert consultant for data modeling, metrics definition, business intelligence, and analytical frameworks. Use proactively for data modeling guidance, metrics framework design, BI architecture recommendations, dbt project optimization, and translating business requirements into analytical specifications. This agent…
database-infrastructure-specialist
Expert consultant for database architecture, performance tuning, and data management strategies. Use proactively for database design, performance optimization, scalability planning, high availability strategies, data security, and migration planning. Provides analysis and recommendations without writing code. When you…
database-architect
Expert consultant for database design, query optimization, data modeling, and performance tuning. Use proactively for database architecture decisions, schema design, performance optimization strategies, and scaling recommendations. When you prompt this agent, describe exactly what you want them to do in as much detail…
database-architect
Database architect specializing in schema design, query optimization, and zero-downtime migrations.
dba
Database Architect / DBA role. Use when you need to design database schemas, table structures, indexing strategy, or data security design. Engages after architecture design is complete and before backend development begins.
db-architect
Specialist for schema design, migrations, query optimization, and data security (RLS). Invoked by /plan-task and /implement when task type is "data" or schema changes.