deep-research

A structured workflow for researching important questions by listing competing explanations, testing them against evidence, and checking how sensitive the conclusion is to new information.

In plain words
What is it for?
Use it to investigate claims, validate or disprove ideas, compare explanations, and produce source-linked conclusions with a confidence level.
Why use it?
It reduces the risk of accepting the first plausible answer, especially when the decision has serious consequences. It also makes the evidence and uncertainty explicit.

Skill for Claude CodeCodex

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/5uck1ess/devkit/deep-research
Any agent
npx skills add 5uck1ess/devkit --skill deep-research
Clone the repo
git clone --depth 1 https://github.com/5uck1ess/devkit

Made for: Claude Code, Codex.

Per session 223 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 501 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 $0.00223 $0.00501
Opus 5 $0.00112 $0.00251
Sonnet 5 $0.00045 $0.00100
Haiku 4.5 $0.00022 $0.00050

Measured 2d ago against content hash f9ded86b7c66, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

deep-research 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.

skills/deep-research/SKILL.md · 31 lines

What it actually says

Deep Research

ACH-enhanced deterministic research: clarify → perspectives → decompose → parallel search → extract claims → hypotheses → disconfirm → evidence matrix (with sensitivity check) → self-critique → synthesize.

Costs more tokens (~400k budget) but produces higher-confidence results by actively trying to disprove answers.

Invoke

Start the workflow via the devkit engine:

Use the devkit_start tool with workflow: "deep-research" and input: "{input}".

Then follow each step the engine returns. Call devkit_advance after completing each step. The engine controls step order, gates, and loops. Do NOT skip steps.

Rules

  • Perspectives first — ground queries in real viewpoints, not LLM brainstorming
  • Disconfirm > confirm — try to KILL hypotheses, not prove them
  • Summarize immediately — never carry raw fetched content forward
  • Evidence matrix is mandatory — no skipping the structured comparison
  • Sensitivity check is mandatory — know how fragile your conclusion is
  • Self-critique before output — catch your own biases
  • Cite everything — every claim links to its source
  • Confidence calibration — HIGH/MEDIUM/LOW based on evidence robustness, not gut feel
  • Be honest about uncertainty — "I don't know" with good reasoning beats a confident wrong answer
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 · 31 lines · 223 tokens per session scan A f9ded86b7c66

Subscribe to this mod's changes

deep-research is a skill published in the GitHub repository 5uck1ess/devkit (5 stars, last pushed 13d ago), licensed MIT. It adds 223 tokens to every session and 501 once invoked, about $0.0011 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.

Related

Other skills, from other repositories