deep-search

deep-search is a skill for Claude Code from yohn1985/jarvisbot. It costs 34 tokens per session (408 once invoked), scanned A, original, Apache-2.0.

A repository investigation skill that traces a bug or design question across code, explores related paths in parallel, and produces a checked plan. A repository is a project's source-code collection; ripgrep is a fast text-search tool.

In plain words
What is it for?
Use it to find the source and impact of a bug or design question across one or more repositories, with file-and-line findings and a red-team verdict.
Why use it?
It reduces the risk of fixing one file while missing related code elsewhere, and tests the final explanation for gaps.

Skill for Claude Code

Written for Claude Code: when-to-use in frontmatter. Also seen: mentions Codex.

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 skills/yohn1985/jarvisbot/deep-search
Any agent
npx skills add yohn1985/jarvisbot --skill deep-search
Clone the repo
git clone --depth 1 https://github.com/yohn1985/jarvisbot

Made for: Claude Code.

Wrote 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.

agentmods badge for deep-search

README.md
[![agentmods](https://agentmods.dev/badge/skills/yohn1985/jarvisbot/deep-search.svg)](https://agentmods.dev/skills/yohn1985/jarvisbot/deep-search)
Your own site
<a href="https://agentmods.dev/skills/yohn1985/jarvisbot/deep-search"><img src="https://agentmods.dev/badge/skills/yohn1985/jarvisbot/deep-search.svg" alt="Measured on agentmods" height="20"></a>
Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 408 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 5.1 $0.00034 $0.00408
Opus 5 $0.00017 $0.00204
Sonnet 5 $0.00007 $0.00082
Haiku 4.5 $0.00003 $0.00041

Measured 5d ago against content hash 8b5b49a34e50, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

deep-search 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 5d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (skill.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/deep-search/SKILL.md · 37 lines

What it actually says

The open-source distillation of the deep-fix method: approximate a long-horizon mind on a finite-context model by externalizing the work.

LOCATE (LLM)  → the blast-radius center (seed identifiers)
TRACE  (rg)   → map the blast radius across the repos
EXPLORE (LLM) → parallel dense findings packs (one per thread)
SYNTHESIZE (LLM) → a plan across ALL paths
RED-TEAM (LLM) → prove the conclusion wrong/incomplete before trusting it

Runs entirely on Jarvis's configured LLM router (claude/codex/ollama) + ripgrep — no environment coupling, so it's public. The judgment points (locate/synthesize/red-team) route to the strong model; exploration can route cheaper.

Usage

./install.sh skill run deep-search "why does add-to-waba 400 before calling Meta" --repos /path/to/repo
./install.sh skill run deep-search "<bug or design question>" --leaves 6

Repos default to deep_search.repos in config (or the current directory).

Output

A root-caused plan (file:line across all swept sites) + a red-team verdict (survives|broken). The value is the sweep + self-audit, not a single-file answer.

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 5d ago First seen · 37 lines · 34 tokens per session scan A 8b5b49a34e50

Subscribe to this mod's changes

deep-search is a skill published in the GitHub repository yohn1985/jarvisbot (1 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 34 tokens to every session and 408 once invoked, about $0.0002 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.