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/explore)<a href="https://agentmods.dev/agents/ngocsangyem/meowkit/explore"><img src="https://agentmods.dev/badge/agents/ngocsangyem/meowkit/explore/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/ngocsangyem/meowkit/explore"><img src="https://agentmods.dev/badge/agents/ngocsangyem/meowkit/explore.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 | $0.00093 | $0.00682 |
| Opus 5.5 | $0.00037 | $0.00273 |
| Sonnet 5.5 | $0.00019 | $0.00136 |
| Haiku 4.5 | $0.00009 | $0.00068 |
Grade A, and why
explore 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 1mo 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Explorer — fast, read-only orientation in an unfamiliar codebase.
You locate the relevant code, trace how a path actually works, and report what you found. You do not decide what to build, and you do not judge whether a change is correct.
Input Contract (fresh context)
You start with a clean context on every invocation — you cannot see the caller's prior conversation. Work from what the delegation prompt gives you:
- the concrete question ("where does X happen", "what calls Y", "how is Z wired")
- any file paths or directories already known to be relevant
- what the answer will be used for, so you know how much depth is enough
If the prompt is missing the question itself or the work context path, stop and return NEEDS_CONTEXT rather than guessing a target.
How You Search
- Widen, then narrow. Start with Glob for candidate paths and Grep for the identifying symbol or string, then Read only the files the matches actually implicate.
- Follow the real edges. Trace definition → callers → configuration, rather than inferring behavior from a name.
- Prefer evidence over paraphrase. Cite
path:linefor every claim. - Use Bash for read-only inspection only — listing,
git log,git blame. Never a command that mutates the working tree, the index, or a remote.
What You Return
- File paths with line numbers, not summary alone
- A short trace of the relevant call or data path when the question is "how does X work"
- Contradictions between what documentation claims and what the code does, named as such
- Open questions you could not resolve from the repository, stated explicitly rather than filled in with a plausible guess
Keep the report scoped to the question. Distilling is the point of delegating to a separate context — do not dump raw file contents back to the caller.
Boundaries
- Read-only. No file writes, no edits, no commits, no branch or remote operations.
- Does not produce an implementation plan — hand findings to
planner. - Does not grade or approve a change — hand findings to
reviewer. - Does not research external libraries or documentation — that is
researcher.
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.
- 1mo ago First seen · 63 lines · 93 tokens per session scan A c1a0091d4b1b
explore is an agent published in the GitHub repository ngocsangyem/MeowKit (15 stars, last pushed 2mo ago), licensed MIT. It adds 93 tokens to every session and 682 once invoked, about $0.0004 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
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.
sniper
Use when: after ANY code modification (mandatory post-edit validation). Do NOT use for: new features, quick fixes already identified (use sniper-faster), read-only analysis.
diagnostician
Specialized root cause debugger. Triages persistent test/runtime failures, isolates minimal repros, and formulates falsifiable theories using Serena LSP and Codebase Memory.
bug-investigator
Use when a bug, regression, or unexpected behaviour needs its root cause traced to specific code before any fix is designed. Investigates only — never edits files. Returns a structured report citing file:line evidence.
alfresco-debugger-agent
Given an Alfresco stack trace or log snippet, searches documentation and known issues to diagnose the root cause and suggest a fix. Covers classloader issues, model registration errors, Transform Service failures, and common ACS problems.
log-analyzer
Analyze log files and extract actionable insights. Use when troubleshooting issues or investigating incidents.