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 B143KC47/deep-research-skill --skill deep-researchgit clone --depth 1 https://github.com/B143KC47/deep-research-skillWrote 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/b143kc47/deep-research-skill/deep-research)<a href="https://agentmods.dev/skills/b143kc47/deep-research-skill/deep-research"><img src="https://agentmods.dev/badge/skills/b143kc47/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.
<a href="https://agentmods.dev/skills/b143kc47/deep-research-skill/deep-research"><img src="https://agentmods.dev/badge/skills/b143kc47/deep-research-skill/deep-research.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 | $0.00083 | $0.01851 |
| Opus 5 | $0.00042 | $0.00925 |
| Sonnet 5 | $0.00017 | $0.00370 |
| Haiku 4.5 | $0.00008 | $0.00185 |
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 8d 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.
How it starts
The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deep Research
Run adaptive, evidence-backed research across broad source classes while keeping claims auditable. The goal is not a fixed number of hops: search widely enough, verify strongly enough, and stop when the answer is well supported or the remaining uncertainty is explicit. Keep private reasoning concise; record public, auditable artifacts: queries, sources, claims, limitations, and evidence IDs.
When to activate, and at what effort
Do not activate for a simple fact, rewrite, translation, summary of provided text, or casual chat — or when the user says to answer only from provided material. If borderline, prefer a quick normal answer unless the user asks for citations, verification, current information, source comparison, or decision-grade evidence.
Otherwise pick effort by risk and ambiguity:
| Effort | Budget | Use for |
|---|---|---|
quick |
2-4 hops, 2+ source classes | narrow, low-risk verification or citations |
standard |
5-8 hops, 3+ classes | researched synthesis, current-info checks, tool comparison, claim verification |
deep |
9-14 hops, 4+ classes | literature review, paper review, GitHub due diligence, implementation recommendation, local files + web verification |
exhaustive |
15+ hops or user budget, 5+ classes | high-stakes, contested, fast-changing, or legal/medical/financial/security-sensitive topics; explicit requests for comprehensive coverage |
If the user did not specify scope, infer a reasonable one, state the assumption briefly, and proceed. Ask for clarification only when the missing detail would change the research target or make the answer unsafe.
Runtime setup
Use the bundled ledger script for nontrivial research so the run has auditable artifacts. In ChatGPT-style sandboxes the skill directory is normally SKILL_DIR=/home/oai/skills/deep-research; otherwise locate the installed deep-research directory. Store run artifacts in a writable task workspace (prefer /mnt/data/research_runs), never inside the skill directory.
What ships with it
14 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.
- agents/openai.yaml 169 B
- references/bibliography.md 4.0 KB
- references/evaluation.md 9.1 KB
- references/openclaw-install.md 2.5 KB
- references/project-and-paper-patterns.md 4.8 KB
- references/query-playbook.md 7.4 KB
- references/report-template.md 3.3 KB
- references/research-protocol.md 8.2 KB
- references/source-quality.md 7.6 KB
- scripts/research_ledger.py 33 KB runs code
- tests/eval_prompts.yaml 5.0 KB
- tests/fixtures/local_claims.md 167 B
- tests/fixtures/prompt_injection_readme.md 224 B
- tests/test_research_ledger.py 7.9 KB runs code
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.
- 8d ago First seen · 105 lines · 83 tokens per session scan A a31ac927bbda
deep-research is a skill published in the GitHub repository B143KC47/deep-research-skill (2 stars, last pushed 2mo ago), licensed MIT. It adds 83 tokens to every session and 1,851 once invoked, about $0.0004 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.
Other skills, from other repositories
workflow-patterns
Argument shapes for the 5 built-in workflow patterns — deep-research, adversarial-review, code-review, multi-perspective, codebase-audit — runnable via the workflow tool's name input, without slash-command syntax. Use for requests like "research X", "fact-check/adversarially review this", "review this diff/PR"…
workflow-authoring
Guidance for writing, editing, reviewing, and debugging JavaScript workflow code for pi-dynamic-workflows. Use when authoring or changing workflow scripts; not for merely running an existing workflow.
lain
Structural code intelligence for AI coding agents. Use this skill when the user wants to understand how a codebase is organized (modules, call graphs, file dependencies), find where to start reading, trace the impact of a change, find code by meaning, or understand what a symbol does in its full context. Do NOT use…
create-modal
Create declarative modals using the modal library API. Covers modal types (confirm, input, select, form), sections (Text, Buttons, Input, Textarea, Checkbox, Select, List, Combo, When, Custom), rendering with OverlayModal, and keyboard/mouse handling. Use when adding modals or dialogs to the application.
autoprompt
Explicit-only useful-first orchestration. Invoke /autoprompt to turn a mission into one executable roadmap, build dependency-safe lanes, and verify the result with independent reviewers. Never infer invocation from ordinary requests. Never resume from leftover artifacts without an explicit resume instruction.
merge-strategy
Git merge strategies, conflict resolution approaches, merge vs rebase recommendations, and branch integration patterns in sidecar. Covers pull strategy menu, direct merge workflow, squash merge, commit message templates, configurable defaults, and protected branches. Use when working on git merge features or making…