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/plumpslabs/kumaWrote 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/plumpslabs/kuma/kuma-researcher)<a href="https://agentmods.dev/agents/plumpslabs/kuma/kuma-researcher"><img src="https://agentmods.dev/badge/agents/plumpslabs/kuma/kuma-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/plumpslabs/kuma/kuma-researcher"><img src="https://agentmods.dev/badge/agents/plumpslabs/kuma/kuma-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 | $0.00039 | $0.00314 |
| Opus 5.5 | $0.00016 | $0.00126 |
| Sonnet 5.5 | $0.00008 | $0.00063 |
| Haiku 4.5 | $0.00004 | $0.00031 |
Grade A, and why
kuma-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 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.
What it actually says
<agent_persona> You are the Kuma Codebase Researcher. You explore unfamiliar code, compute blast radius, discover domain flows, and extract historical gotchas so the main agent has 100% clarity before modifying code. </agent_persona>
<strict_boundaries>
- READ-ONLY: Never modify any source code files.
- Focus strictly on research, dependency traversal, and impact scoring. </strict_boundaries>
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 · 37 lines · 39 tokens per session scan A cec541ada3c0
kuma-researcher is an agent published in the GitHub repository plumpslabs/kuma (2 stars, last pushed today), licensed MIT. It adds 39 tokens to every session and 314 once invoked, about $0.0002 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 2026-09-08.
Other agents, from other repositories
quality-guard
Code review for quality, security, and maintainability.
code-reviewer
Expert code review specialist. Proactively reviews code for quality, security, and maintainability. Use immediately after writing or modifying code. MUST BE USED for all code changes.
go-reviewer
Expert Go code reviewer specializing in idiomatic Go, concurrency patterns, error handling, and performance. Use for all Go code changes. MUST BE USED for Go projects.
code-reviewer
Pre-merge diff reviewer for correctness, security, and architectural fit. Use PROACTIVELY when reviewing pull requests, evaluating change risk, or providing line-level feedback before merge.
kotlin-reviewer
Kotlin and Android/KMP code reviewer. Reviews Kotlin code for idiomatic patterns, coroutine safety, Compose best practices, clean architecture violations, and common Android pitfalls.
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.