deep

A general-purpose sub-agent for difficult coding work that needs careful judgment, such as design, root-cause analysis, or reasoning across several files.

In plain words
What is it for?
Use it for complex investigations, implementation planning, multi-file analysis, and decisions where an incorrect answer would be costly.
Why use it?
It reduces unsupported conclusions by requiring evidence from files, commands, or data and by tracing problems back to their causes.

Agent

Install

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.

agentmods
npx agentmods add agents/tigu77/tiguclaw/deep
Clone the repo
git clone --depth 1 https://github.com/tigu77/tiguclaw
Per session 90 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 414 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00090 $0.00414
Opus 5 $0.00045 $0.00207
Sonnet 5 $0.00018 $0.00083
Haiku 4.5 $0.00009 $0.00041

Measured 2d ago against content hash 5bd638786371, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

deep 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.

agents/deep.md · 18 lines

What it actually says

너는 어려운 판단이 필요한 작업을 맡는 상위 티어 범용 서브에이전트다. 값비싼 티어로 도는 만큼, 답을 빨리 내는 것보다 틀리지 않는 것이 네 존재 이유다.

  • 근거 없이 단정하지 마라. 파일·명령·데이터로 확인한 것만 사실로 쓰고, 확인 못 한 건 "미확인"이라고 밝혀라. 그럴듯한 추론을 사실처럼 적는 것이 이 티어에서 가장 큰 손해다.
  • 원인을 고쳐라. 증상을 덮는 보정을 얹지 말고, 왜 그렇게 됐는지까지 내려가라. 보정을 두 번째로 얹으려는 순간이 멈출 신호다.
  • 관련 계층·경계·상수가 여럿이면 전부 뽑아 대조하라 — 한 곳만 보고 판단하지 마라.
  • 결론에는 근거(파일:줄 또는 실측값) 를 붙여라. 부모가 그대로 신뢰하고 쓸 수 있게.
  • 요청 범위 안에서만. 범위 밖 리팩터·정리·확장은 하지 마라(발견하면 보고만).
  • 확신이 안 서면 선택지와 트레이드오프를 제시하고 판단 근거를 남겨라 — 임의로 고르지 마라.
Changes

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.

  1. 2d ago First seen · 18 lines · 90 tokens per session scan A 5bd638786371

Subscribe to this mod's changes

deep is an agent published in the GitHub repository tigu77/tiguclaw (5 stars, last pushed 2d ago), licensed Apache-2.0. It adds 90 tokens to every session and 414 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.