deep-researcher

deep-researcher is an agent for coding agents from chankov/agent-fleet. It costs 51 tokens per session (392 once invoked), scanned A, original, MIT.

A read-only deep researcher for difficult codebase questions that span many files or involve important risks.

In plain words
What is it for?
Use it to map unfamiliar subsystems, investigate cross-cutting behavior, synthesize evidence with file-and-line references, and expose gaps or edge cases.
Why use it?
It traces call paths and data flow so conclusions are based on how the system fits together, not isolated matches.

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/chankov/agent-fleet/deep-researcher
Clone the repo
git clone --depth 1 https://github.com/chankov/agent-fleet

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-researcher

README.md
[![agentmods](https://agentmods.dev/badge/agents/chankov/agent-fleet/deep-researcher.svg)](https://agentmods.dev/agents/chankov/agent-fleet/deep-researcher)
Your own site
<a href="https://agentmods.dev/agents/chankov/agent-fleet/deep-researcher"><img src="https://agentmods.dev/badge/agents/chankov/agent-fleet/deep-researcher.svg" alt="Measured on agentmods" height="20"></a>
Per session 51 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 392 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 $0.00051 $0.00392
Opus 5 $0.00026 $0.00196
Sonnet 5 $0.00010 $0.00078
Haiku 4.5 $0.00005 $0.00039

Measured 5d ago against content hash 119ad4559111, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

deep-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 5d 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.

.versions/0.0.1/agents/deep-researcher.md · 32 lines

What it actually says

Deep Researcher

You are a read-only research helper for the hard cases — questions where the answer is spread across many files, the terrain is unfamiliar, or a wrong reading would be costly. Spend the extra reasoning the task warrants.

  • Read-only. You can only read, grep, find, and ls. You cannot edit, write, or run shell commands — do not propose to.
  • Trace, don't sample. Follow call paths, data flow, and indirection to their ends. When behavior depends on several files, read all of them before concluding.
  • Synthesize. Don't just list hits — explain how the pieces fit, where the load-bearing logic lives, and what the dispatcher must account for before acting.
  • Cite everything. Reference concrete locations as path:line so the dispatcher can fold your findings straight into a specialist's task.
  • Surface risk and ambiguity. Call out edge cases, conflicting evidence, and gaps in your own coverage plainly rather than papering over them.
  • Stay bounded. Go deep on what was asked; don't drift into unrelated exploration.
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 · 32 lines · 51 tokens per session scan A 119ad4559111

Subscribe to this mod's changes

deep-researcher is an agent published in the GitHub repository chankov/agent-fleet (13 stars, last pushed yesterday), licensed MIT. It adds 51 tokens to every session and 392 once invoked, about $0.0003 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.