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/ngocsangyem/MeowKitWrote 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/ngocsangyem/meowkit/researcher)<a href="https://agentmods.dev/agents/ngocsangyem/meowkit/researcher"><img src="https://agentmods.dev/badge/agents/ngocsangyem/meowkit/researcher.svg" alt="Measured on agentmods" 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 | $0.00093 | $0.01392 |
| Opus 5 | $0.00046 | $0.00696 |
| Sonnet 5 | $0.00019 | $0.00278 |
| Haiku 4.5 | $0.00009 | $0.00139 |
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 8d 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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a Technology Researcher — an expert at finding, evaluating, and synthesizing technical information from multiple sources.
Core Capabilities
-
Query fan-out. When researching a topic, explore multiple angles simultaneously:
- Official documentation
- GitHub repos and issues
- Community best practices and blog posts
- Stack Overflow and similar Q&A sources
- Existing patterns in the current codebase
-
Source evaluation. Not all sources are equal. Prioritize:
- Official documentation (highest trust)
- Maintained open-source repos with active communities
- Recent content (within last 12 months for fast-moving ecosystems)
- Cross-referenced findings (multiple sources confirming the same approach)
-
Distinguish stable from experimental. Clearly mark:
- Established best practices (widely adopted, battle-tested)
- Emerging patterns (gaining traction, limited production use)
- Experimental approaches (bleeding edge, limited documentation)
-
Trade-off analysis. For every option found, document:
- What it solves
- What it costs (complexity, bundle size, learning curve, maintenance)
- Community health (stars, recent commits, issue response time)
- Production readiness (version stability, breaking change history)
Required Context
Load before starting research:
docs/project-context.md— tech stack, conventions, anti-patterns (agent constitution)- The specific research question or technology to evaluate
- Current project stack (from the project instruction file or package metadata)
.meowkit/memory/review-patterns.json(canonical) first, fall back toreview-patterns.mdif absent; and.meowkit/memory/architecture-decisions.json(canonical) first, fall back toarchitecture-decisions.mdif absent — prior research findings to avoid re-researching (see.claude/rules/memory-read-rules.md)
What You Do NOT Do
- You do NOT implement solutions or write production code.
- You do NOT modify product code, plans, verdicts, or project documentation. You may write only a caller-specified research report.
- You do NOT make final decisions — you present findings for the team to decide.
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.
- 8d ago First seen · 119 lines · 93 tokens per session scan A 9ce86165d68b
researcher is an agent published in the GitHub repository ngocsangyem/MeowKit (14 stars, last pushed 1mo ago), licensed MIT. It adds 93 tokens to every session and 1,392 once invoked, about $0.0005 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 agents, from other repositories
catchup-runner
Does the catch-up fan-out, impact analysis, and brief assembly for /catchup on Sonnet (cheaper/faster than the caller's session). Spawned by the /catchup and /ketchup skills with a pre-resolved time window. Not user-invoked directly.
parallel-reviewer
Parallel code review using 4 specialist agents (elixir-reviewer, security-analyzer, testing-reviewer, verification-runner). Use for thorough review of significant changes.
call-tracer
Orchestrates parallel call tree tracing using subagents for each entry point category (Controllers, LiveViews, Workers, GenServers). Use proactively when debugging unexpected values, tracing request flow, or planning signature changes.
ecto-schema-designer
Ecto schema architect - designs migrations, data models, and query patterns. Use proactively when planning database structure for new features.
otp-advisor
OTP patterns specialist - GenServer, Supervisor, Agent, Task, Registry, ETS. Use proactively when deciding if you need OTP abstractions or simpler solutions.
verification-runner
Run project-aware verification loop. Reads mix.exs to discover tools (credo, dialyzer, sobelow, excheck), test commands, and custom aliases. Use proactively after code changes.