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 skills add yohn1985/jarvisbot --skill deep-searchgit clone --depth 1 https://github.com/yohn1985/jarvisbotWrote 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/skills/yohn1985/jarvisbot/deep-search)<a href="https://agentmods.dev/skills/yohn1985/jarvisbot/deep-search"><img src="https://agentmods.dev/badge/skills/yohn1985/jarvisbot/deep-search/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/skills/yohn1985/jarvisbot/deep-search"><img src="https://agentmods.dev/badge/skills/yohn1985/jarvisbot/deep-search.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 | $0.00034 | $0.00408 |
| Opus 5.5 | $0.00014 | $0.00163 |
| Sonnet 5.5 | $0.00007 | $0.00082 |
| Haiku 4.5 | $0.00003 | $0.00041 |
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 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
deep-search
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.
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.
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 · 34 tokens per session scan A 8b5b49a34e50
deep-search is a skill published in the GitHub repository yohn1985/jarvisbot (1 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 34 tokens to every session and 408 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
agent-performance-optimizer
Agent skill for performance-optimizer - invoke with $agent-performance-optimizer.
agent-refinement
Agent skill for refinement - invoke with $agent-refinement.
diag-harness
Kernel-version skew check (ADR-027). Reports manifest surface + manifest kernel + installed kernel + verdict (match/patch-diff/minor-diff/major-diff). Exits 1 on minor/major skew with a copy-pasteable npm install @metaharness/[email protected] next step. Exits 2 if no .harness/manifest.json at path.
evidence-audit
Evidence-led audit/fix rounds for any codebase in any language. Finds only defects that a runnable proof reproduces on current code, applies the narrowest in-scope patch, verifies with a second proof, promotes high-risk proofs to permanent regression tests, and reports exact validation results. Use whenever the user…
bug-hunter
Use this skill when scanning source code for bugs, anti-patterns, code smells, or quality issues in a codebase, or when running a proof-driven bug hunt that must find, prove, fix, and verify one real defect. Trigger on the explicit vocabulary — "bug", "bug hunt", "/bughunt", "scan for issues", "find problems"…
debugging
Use this skill when something is broken and the cause is unknown — a failing test, a crash, an error message, wrong output, a regression, a hang, or behaviour that differs between environments — and it has to be found and fixed at the root. Also use it to build the failing proof for a suspected defect before fixing…