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 johnqtcg/awesome-skills --skill deep-researchgit clone --depth 1 https://github.com/johnqtcg/awesome-skillsWrote 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/johnqtcg/awesome-skills/deep-research)<a href="https://agentmods.dev/skills/johnqtcg/awesome-skills/deep-research"><img src="https://agentmods.dev/badge/skills/johnqtcg/awesome-skills/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/johnqtcg/awesome-skills/deep-research"><img src="https://agentmods.dev/badge/skills/johnqtcg/awesome-skills/deep-research.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00074 | $0.05975 |
| Opus 5 | $0.00037 | $0.02988 |
| Sonnet 5 | $0.00015 | $0.01195 |
| Haiku 4.5 | $0.00007 | $0.00598 |
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 yesterday.
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 — 500 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deep Research
Produce research whose claims can be traced to content actually read or repository artifacts actually observed.
Quick Reference
| Need | Action |
|---|---|
| Classify `web | codebase |
| Enforce cumulative query, extraction, and report-source ceilings | Reuse the session artifact created by plan --output |
| Author findings JSON | Load references/output-contract-template.md |
| Assess hallucination, confidence, or source quality | Load references/hallucination-and-verification.md |
| Understand Web trust boundaries and safe egress | Load references/web-evidence-and-egress.md |
| Apply programmer-specific query/evidence patterns | Load references/research-patterns.md |
| Claim runtime behavior from tests | Load references/test-receipt-schema.md |
Mandatory Gates
Execute gates in strict order. Stop when a gate blocks later work.
1) Scope → 2) Ambiguity → 3) Evidence → 4) Research Mode
→ 5) Hallucination Awareness → 6) Budget Control
→ 7) Content Extraction → 8) Execution Integrity
1) Scope Classification Gate
Select one research kind and one goal.
- Research kind:
web | codebase | hybrid - Category: comparison, trend, claim verification, technical deep-dive, codebase audit
- Goal: Know, Compare, Verify, Recommend, or Audit
Run the executable classifier:
python3 scripts/deep_research.py plan \
--request "<user request>" \
--output /tmp/research_plan.json
The output is a versioned session ledger, not a disposable plan. Reuse that exact file for every budget-consuming command in the research run.
Use codebase when the answer depends only on local code, commits, or test results. Do not perform web retrieval merely to manufacture URLs. Use hybrid only when external evidence is part of the question.
2) Ambiguity Resolution Gate
STOP and ASK when scope, comparison dimensions, time window, or success criteria would materially change the research. Do not ask again for constraints already supplied.
What ships with it
43 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.
- references/hallucination-and-verification.md 14 KB
- references/output-contract-template.md 9.2 KB
- references/research-patterns.md 8.6 KB
- references/source-authority-registry.json 9.4 KB
- references/test-receipt-schema.md 5.0 KB
- references/web-evidence-and-egress.md 5.1 KB
- scripts/deep_research_lib/__init__.py 65 B runs code
- scripts/deep_research_lib/authority.py 4.4 KB runs code
- scripts/deep_research_lib/claim_support.py 14 KB runs code
- scripts/deep_research_lib/planning.py 8.4 KB runs code
- scripts/deep_research_lib/reporting.py 3.1 KB runs code
- scripts/deep_research_lib/repository.py 26 KB runs code
- scripts/deep_research_lib/session.py 9.3 KB runs code
- scripts/deep_research_lib/web.py 10 KB runs code
- scripts/deep_research.py 116 KB runs code
- scripts/run_regression.sh 771 B runs code
- scripts/tests/claim_support_corpus.json 8.7 KB
- scripts/tests/COVERAGE.md 10 KB
- scripts/tests/golden/behavior_confidence_high.json 643 B
- scripts/tests/golden/behavior_confidence_medium.json 684 B
- scripts/tests/golden/behavior_degradation_blocked.json 638 B
- scripts/tests/golden/behavior_mode_deep_security.json 719 B
- scripts/tests/golden/behavior_mode_quick.json 522 B
- scripts/tests/golden/behavior_mode_user_override.json 649 B
- scripts/tests/golden/codebase_research.json 230 B
- scripts/tests/golden/error_debugging.json 217 B
- scripts/tests/golden/evidence_chain.json 279 B
- scripts/tests/golden/fp_codebase_no_web_retrieval.json 679 B
- scripts/tests/golden/fp_quick_prevents_over_research.json 627 B
- scripts/tests/golden/hallucination_awareness.json 269 B
- scripts/tests/golden/performance_benchmark.json 242 B
- scripts/tests/golden/security_research.json 205 B
- scripts/tests/golden/tech_comparison.json 265 B
- scripts/tests/golden/tool_selection_principles.json 230 B
- scripts/tests/test_claim_support.py 21 KB runs code
- scripts/tests/test_deep_research.py 40 KB runs code
- scripts/tests/test_evidence_integrity.py 41 KB runs code
- scripts/tests/test_golden_scenarios.py 12 KB runs code
- scripts/tests/test_repository_integrity.py 33 KB runs code
- scripts/tests/test_session_budget.py 14 KB runs code
- scripts/tests/test_skill_contract.py 22 KB runs code
- scripts/tests/test_subcommand_smoke.py 16 KB runs code
- scripts/tests/test_web_security.py 3.3 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.
- yesterday Changed · +37 lines 0925cebddbd8
- 11d ago First seen · 463 lines · 74 tokens per session scan A b843ec8dffc2
deep-research is a skill published in the GitHub repository johnqtcg/awesome-skills (30 stars, last pushed today), licensed MIT. It adds 74 tokens to every session and 5,975 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 2026-08-30.
Other skills, from other repositories
security-compliance
Guides security professionals in implementing defense-in-depth security architectures, achieving compliance with industry frameworks (SOC2, ISO27001, GDPR, HIPAA), conducting threat modeling and risk assessments, managing security operations and incident response, and embedding security throughout the SDLC.
stride-analysis-patterns
Apply STRIDE methodology to systematically identify threats. Use when analyzing system security, conducting threat modeling sessions, or creating security documentation.
cache-components
Expert guidance for Next.js Cache Components and Partial Prerendering (PPR). PROACTIVE ACTIVATION: Use this skill automatically when working in Next.js projects that have cacheComponents: true in their next.config.ts/next.config.js. When this config is detected, proactively apply Cache Components patterns and best…
manage-skills
A maintenance workflow for checking whether project verification skills still cover the code and rules that changed during a session.
blind-spot-pass
Use before starting work in a domain you don't know well, to surface the "unknown unknowns" — the things you don't even know to ask about — and learn just enough to prompt and decide well. Implements the "blind spot pass" pattern from Anthropic's Fable "finding your unknowns" field guide. Triggers when you say "I'm…
skill-factory
A workflow that examines completed session work and turns reusable patterns into Claude Code skills.