What is deep-research?

A structured process for researching broad or important questions with evidence grading, citations, review, and explicit stopping rules. It separates facts, interpretation, uncertainty, and proposed actions.

Use it for consensus reviews, evidence maps, comparisons, personalized research, and other questions that need more than a quick search.

It reduces unsupported conclusions and makes the research trail easier to check and reuse.

deep-research — Skill for Codex by tonyazhuuki/deep-research-skill

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.

Any agent

npx skills add tonyazhuuki/deep-research-skill --skill deep-research

Clone the repo

git clone --depth 1 https://github.com/tonyazhuuki/deep-research-skill

Made for: Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/tonyazhuuki/deep-research-skill/deep-research/github.svg)](https://agentmods.dev/skills/tonyazhuuki/deep-research-skill/deep-research)

Your own site

<a href="https://agentmods.dev/skills/tonyazhuuki/deep-research-skill/deep-research"><img src="https://agentmods.dev/badge/skills/tonyazhuuki/deep-research-skill/deep-research/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/tonyazhuuki/deep-research-skill/deep-research"><img src="https://agentmods.dev/badge/skills/tonyazhuuki/deep-research-skill/deep-research.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 64 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 837 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00064	$0.00837
Opus 5.5	$0.00026	$0.00335
Sonnet 5.5	$0.00013	$0.00167
Haiku 4.5	$0.00006	$0.00084

Measured 15d ago against content hash 645a684fe1e4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 15d ago.

The scan reads SKILL.md. This mod also ships 3 executable files (scripts/validate_run.py, scripts/validate_skill.py, tests/test_validators.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.

codex/deep-research/SKILL.md · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Deep Research

Produce a traceable answer, not an impressive pile of sources. Keep facts, interpretation, uncertainty, and proposed actions separate.

Start safely

Read repository instructions and the nearest scoped rules.
Classify the request: consensus, evidence-map, comparative, personalized, or full.
Record the research question, decision it should support, domain, exclusions, output location, and authorization boundary.
Search existing local consensus material before starting duplicate work.
Treat local or personal data as private by default. Do not send it to external tools unless the user explicitly authorizes that transfer.

Research is read-only by default. Writing the requested research artifacts is allowed; changing plans, protocols, source data, queues, or external systems requires separate authorization.

Load references progressively

Read pipeline.md before every full run.
Read evidence.md before collecting or grading sources.
Read domain-adapters.md for the selected domain.
Read run-contract.md before creating artifacts or validating a run.
Read frameworks.md when converting reviewed research into a reusable knowledge framework.

For a narrow follow-up, use only the relevant sections. For a full run, read all four files.

Execute

Create the run contract and _PROGRESS_LOG.md.
Cycle 1: map the field across independent evidence streams.
Write Reflection 1 and adversarial/methods reviews.
Cycle 2: investigate the highest-value disputes, gaps, mechanisms, and boundary conditions.
Write Reflection 2 with convergence and unresolved conflicts.
Cycle 3: synthesize claims into the mode-specific deliverables.
Complete fact-check, citation audit, domain review, and action map.
Run scripts/validate_run.py RUN_DIR --mode MODE.
If the validator fails, label the run incomplete; never turn missing artifacts or tool failures into a low quality score.

Read the full file on GitHub · 65 lines

Files

What ships with it

9 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.

15d ago First seen · 65 lines · 64 tokens per session scan A 645a684fe1e4

Subscribe to this mod's changes

deep-research is a skill published in the GitHub repository tonyazhuuki/deep-research-skill (32 stars, last pushed 15d ago), licensed MIT. It adds 64 tokens to every session and 837 once invoked, about $0.0003 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 2026-10-23.

Research

deep-research next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
deep-researchtonyazhuuki/deep-research-skill	Skill	32	15d ago	MIT	A	64	Codex
imagegenopenai/codex	Skill	133k	yesterday	Apache-2.0	A	113	Codex
playwright-climicrosoft/playwright	Skill	99k	yesterday	Apache-2.0	A	19	Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	4d ago	MIT	A	200	Claude Code, Codex
systematic-debuggingobra/superpowers	Skill	313k	3d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	95	Claude Code
next-partial-prefetching-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	103	Claude Code