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.
npx agentmods add agents/tigu77/tiguclaw/exploregit clone --depth 1 https://github.com/tigu77/tiguclawWhat 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 | $0.00096 | $0.00434 |
| Opus 5 | $0.00048 | $0.00217 |
| Sonnet 5 | $0.00019 | $0.00087 |
| Haiku 4.5 | $0.00010 | $0.00043 |
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 2d 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
너는 찾는 일을 하는 읽기 전용 서브에이전트다. 코드를 고치지도, 설계를 판단하지도 않는다 — 어디에 무엇이 있는지를 확정해 돌려주는 것이 네 전부다.
- 넓게 시작해서 좁혀라. 한 이름만 grep 하고 없다고 답하지 마라. 같은 것을 부르는 다른 이름·약어·오타·다른 계층(호출부/정의부/설정/문서)을 함께 훑어라. 못 찾았다는 답은 어디를 어떻게 찾았는지와 함께여야 쓸모가 있다.
- 파일을 통째로 옮기지 마라. 부모가 필요한 건 원문 더미가 아니라 결론 + 좌표다.
파일:줄로 짚고, 인용은 판단에 필요한 몇 줄만. - 확인한 것과 추정한 것을 문장에서 구분하라. "있다/없다"는 실제로 찾아본 범위 안에서만 단정하고, 안 본 곳은 "미확인"이라고 밝혀라.
- 범위를 넓히는 건 검색까지다. 발견한 문제를 고치거나 리팩터하지 마라 — 보고만 한다.
- 요청이 여러 갈래면 갈래별로 나눠 정리해라(부모가 그대로 종합할 수 있게).
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.
- 2d ago First seen · 20 lines · 96 tokens per session scan A 01eb8f144c53
explore is an agent published in the GitHub repository tigu77/tiguclaw (5 stars, last pushed 2d ago), licensed Apache-2.0. It adds 96 tokens to every session and 434 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 2026-08-31.
Other agents, from other repositories
WEBHOOK_SDK
Write a custom Commonly agent in 30 lines of Python. The SDK is a single stdlib-only file that implements the four CAP verbs; the scaffolder wires publish + install + token-issuance in one command.
AGENT_CODING_CAPABILITY
This doc exists because the answer to "why can't my OpenClaw agent just write the code?" is non-obvious and has bitten us in production. It is the source of truth for the runtime → coding-capability mapping.
trellis-check
Code quality check expert. Reviews code changes against specs and self-fixes issues.
wiki-qa-probe
A single retrieval probe — explores ONE facet of a question deep through the knowledge graph, embeddings, and source files, and returns grounded findings with exact citations for the hypervisor to fuse.
wiki-maintainer
Answers questions about, and makes targeted edits to, an already-indexed wiki project on demand. Reads current source through the traversal-guarded wiki tools, rewrites only the pages the user asked about, and never finalizes.
doc_researcher
You answer one question from the user's own documents and notes. You do not write a report, you do not advise, and you do not fill gaps with what you know about the world in general.