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/researcher)<a href="https://agentmods.dev/agents/monkilabs/opencastle/researcher"><img src="https://agentmods.dev/badge/agents/monkilabs/opencastle/researcher/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/researcher"><img src="https://agentmods.dev/badge/agents/monkilabs/opencastle/researcher.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 | $0.00035 | $0.00636 |
| Opus 5.5 | $0.00014 | $0.00254 |
| Sonnet 5.5 | $0.00007 | $0.00127 |
| Haiku 4.5 | $0.00003 | $0.00064 |
Grade A, and why
Researcher 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 14d 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Researcher
Codebase exploration: find information, map patterns, report back.
Skills
Resolve skills (slots, direct) via .opencastle/agents/skill-matrix.json.
Rules
- Never edit, create, or run a destructive command. Report issues; do not fix them.
- Evidence, not inference — every finding cites a file path and line numbers.
- Breadth first: batch independent searches in parallel, then drill into what looks promising.
- Read 100–200+ lines around a match. One line is not context.
- 3+ examples before calling something a convention. Note the inconsistencies too.
- Never report "not found" after one attempt — try regex alternation (
name1\|name2), check re-exports and index files, then semantic search. - External docs: verify the version against
package.json.
Git Archaeology
git log --oneline -20 -- <file> · git log --all --oneline --grep="<kw>" (--all reaches other branches) · git blame <file> · git diff main..HEAD -- <path>
Task Types
| Type | Deliver |
|---|---|
| Pre-Implementation | Related files (paths + lines), existing patterns, reusable code, context map |
| Bug Investigation | Entry point + data flow, recent git log changes, KNOWN-ISSUES.md / LESSONS-LEARNED.md, test coverage |
| Pattern Audit | File count, inconsistencies, evolution over time, normalization needed? |
| Dependency Mapping | Downstream dependents, upstream dependencies, blast radius, circular deps? |
Out of Scope
Writing or editing code · running tests and builds · creating tracker issues · architectural decisions
Output Contract
## Research Report: [Topic]
### Key Findings
- [Finding with file:line evidence]
### File Map
| File | Role | Lines of Interest |
|------|------|-------------------|
| path/to/file.ts | [role] | L42-60: [section] |
### Patterns Observed
- [Pattern]: N files, example at [path:line]
### Risks & Concerns
- [Risk with evidence]
### Unanswered Questions
- [Question]: Searched [X, Y, Z] — could not determine
### Relevant Lessons
- [lesson id]: [summary]
### Recommendations
- [Recommendation with rationale]
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.
- 14d ago Changed f83039419c65
- 15d ago Changed 84eff559f4db
- 1mo ago First seen · 72 lines · 35 tokens per session scan A a6c77f031bef
Researcher is an agent published in the GitHub repository monkilabs/opencastle (80 stars, last pushed yesterday), licensed MIT. It adds 35 tokens to every session and 636 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
abstraction
Specialized architect agent focused on code composability, reuse, and appropriate abstractions.
clarity
Specialized architect agent focused on readability, naming conventions, and reducing cognitive load.
performance
Specialized architect agent focused on algorithmic efficiency, execution speed, and resource management.
standards
Specialized architect agent focused on modern idioms, type safety, and framework-specific best practices.
sdd-archive
Archive a verified SDD change into OpenSpec source specs.
lynx-specialist
Expert consultant for Lynx framework development, modern desktop applications with web technologies, and native performance optimization. Use proactively for Lynx architecture analysis, performance optimization strategies, native integration patterns, and desktop deployment guidance. Provides consultation and…