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 insight68/Skills --skill deep-researchgit clone --depth 1 https://github.com/insight68/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/insight68/skills/deep-research)<a href="https://agentmods.dev/skills/insight68/skills/deep-research"><img src="https://agentmods.dev/badge/skills/insight68/skills/deep-research.svg" alt="Measured on agentmods" 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 | $0.00088 | $0.08103 |
| Opus 5 | $0.00044 | $0.04052 |
| Sonnet 5 | $0.00018 | $0.01621 |
| Haiku 4.5 | $0.00009 | $0.00810 |
Grade C, and why
deep-research scanned grade C with 1 finding 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 7d 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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
<!-- All static instructions, methodology, and templates below this line --> This is a copy
100% identical to deep-research — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 857 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deep Research
Core System Instructions
Purpose: Deliver citation-backed, verified research reports through 8-phase pipeline (Scope → Plan → Retrieve → Triangulate → Synthesize → Critique → Refine → Package) with source credibility scoring and progressive context management.
Context Strategy: This skill uses 2025 context engineering best practices:
- Static instructions cached (this section)
- Progressive disclosure (load references only when needed)
- Avoid "loss in the middle" (critical info at start/end, not buried)
- Explicit section markers for context navigation
Decision Tree (Execute First)
Request Analysis
├─ Simple lookup? → STOP: Use WebSearch, not this skill
├─ Debugging? → STOP: Use standard tools, not this skill
└─ Complex analysis needed? → CONTINUE
Mode Selection
├─ Initial exploration? → quick (3 phases, 2-5 min)
├─ Standard research? → standard (6 phases, 5-10 min) [DEFAULT]
├─ Critical decision? → deep (8 phases, 10-20 min)
└─ Comprehensive review? → ultradeep (8+ phases, 20-45 min)
Execution Loop (per phase)
├─ Load phase instructions from [methodology](./reference/methodology.md#phase-N)
├─ Execute phase tasks
├─ Spawn parallel agents if applicable
└─ Update progress
Validation Gate
├─ Run `python scripts/validate_report.py --report [path]`
├─ Pass? → Deliver
└─ Fail? → Fix (max 2 attempts) → Still fails? → Escalate
Workflow (Clarify → Plan → Act → Verify → Report)
AUTONOMY PRINCIPLE: This skill operates independently. Infer assumptions from query context. Only stop for critical errors or incomprehensible queries.
1. Clarify (Rarely Needed - Prefer Autonomy)
DEFAULT: Proceed autonomously. Derive assumptions from query signals.
ONLY ask if CRITICALLY ambiguous:
- Query is incomprehensible (e.g., "research the thing")
- Contradictory requirements (e.g., "quick 50-source ultradeep analysis")
What ships with it
21 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.
- .gitignore 248 B
- ARCHITECTURE_REVIEW.md 15 KB
- AUTONOMY_VERIFICATION.md 12 KB
- COMPETITIVE_ANALYSIS.md 6.0 KB
- CONTEXT_OPTIMIZATION.md 7.4 KB
- QUICK_START.md 4.9 KB
- README.md 9.0 KB
- reference/methodology.md 14 KB
- requirements.txt 454 B
- scripts/citation_manager.py 5.9 KB runs code
- scripts/md_to_html.py 9.7 KB runs code
- scripts/research_engine.py 16 KB runs code
- scripts/source_evaluator.py 9.3 KB runs code
- scripts/validate_report.py 12 KB runs code
- scripts/verify_citations.py 15 KB runs code
- scripts/verify_html.py 7.6 KB runs code
- templates/mckinsey_report_template.html 10 KB
- templates/report_template.md 13 KB
- tests/fixtures/invalid_report.md 288 B
- tests/fixtures/valid_report.md 3.3 KB
- WORD_PRECISION_AUDIT.md 13 KB
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.
- 7d ago First seen · 857 lines · 88 tokens per session scan C af533b36012a
deep-research is a skill published in the GitHub repository insight68/Skills (5 stars, last pushed 5mo ago), licensed MIT. It adds 88 tokens to every session and 8,103 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it C with 1 finding (hidden instructions). It is 100% identical to deep-research, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
humanizar
Reescreve textos em português brasileiro para soarem mais humanos e naturais, reduzindo padrões típicos de escrita gerada por IA sem alterar fatos, argumento ou intenção. Use quando o texto em PT-BR parecer genérico, burocrático ou gerado por IA, ou quando o usuário pedir para "humanizar", "dar vida", "tirar cara de…
aidlc-master
Runs the AWS AI-DLC (AI-Driven Development Life Cycle) methodology end to end: an adaptive three-phase workflow (Inception → Construction → Operations) with human approval gates, a full audit trail, and all artifacts in aidlc-docs/. Use when the user says "Using AI-DLC", "AI-DLC", "AIDLC", "aidlc-master", or asks for…
human-ai
Rewrites English text so it reads as written by a person, without AI writing tics. Removes machine language patterns and AI slop, restores semantic entropy, and injects voice and personality. Use when ENGLISH text reads as generic, bland, or AI-generated - or when asked to "humanize", "de-slop", "remove AI patterns"…
agent-ready-cloudflare
Audit and improve website readiness for AI agents using the Cloudflare "Is It Agent Ready?" scanner (isitagentready.com). Covers scanning via API, interpreting results, generating implementation prompts, and fixing every check. Use when the user mentions "agent ready", "isitagentready", "AI agent scan", "agent…
okf-open-knowledge-format
Create, validate, and enrich Open Knowledge Format (OKF) bundles — the open spec for representing organizational knowledge as markdown files with YAML frontmatter. Use when the user mentions 'OKF', 'Open Knowledge Format', 'knowledge bundle', 'OKF bundle', 'create a knowledge base for agents', 'validate OKF', 'convert…
resume-ats-beater
Este skill deve ser usado para reescrever currículos com foco em compatibilidade ATS e impacto para recrutadores, e/ou auditar perfis LinkedIn para maximizar visibilidade e conversão profissional. Acionar em pedidos de otimização de currículo, melhoria para ATS, reescrita profissional do CV, adaptação para vaga-alvo…