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 agentmods add commands/clchinkc/document-mcp/8-deep-researchgit clone --depth 1 https://github.com/clchinkc/document-mcpWrote 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/commands/clchinkc/document-mcp/8-deep-research)<a href="https://agentmods.dev/commands/clchinkc/document-mcp/8-deep-research"><img src="https://agentmods.dev/badge/commands/clchinkc/document-mcp/8-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 | $0.00000 | $0.00502 |
| Opus 5 | $0.00000 | $0.00251 |
| Sonnet 5 | $0.00000 | $0.00100 |
| Haiku 4.5 | $0.00000 | $0.00050 |
Grade A, and why
8-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 4d 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deep Research & Analysis
Multi-Agent Research Loop: Research → Ultrathink → Write → Review workflow with specialized agents to gather comprehensive information and continuously improve analysis.
Phase 1: Comprehensive Research
Use specialized agents (opus-researcher, behavior-analyst, security-auditor, performance-optimizer) to:
Documentation Analysis:
- Review all documentation in target folders and entire codebase
- Analyze architecture decisions, design principles, and system requirements
- Identify documentation gaps, inconsistencies, or outdated information
- Research external dependencies, frameworks, and best practices
Code Architecture Review:
- Examine all implementation files for fundamental principles and concrete implementation patterns
- Understand system design: complexity vs. usefulness vs. extensibility trade-offs
- Identify premature optimization, overly complex configuration, unnecessary fallbacks
- Map data flow, component relationships, and integration points
- Mark exact code locations for reference (file:line format)
Testing Infrastructure Analysis:
- Review all test files for purpose, pass/fail conditions, and coverage gaps
- Analyze testing strategy effectiveness and identify areas for improvement
- Evaluate test reliability, performance, and maintenance overhead
- Consider how to ensure implementation correctness with optimal resource usage
Phase 2: Continuous Improvement Loop
Iterative Analysis Process:
- Research: Gather information using multiple specialized agents
- Ultrathink: Deep analysis, critique, and evaluation of findings
- Write: Document insights, patterns, and recommendations
- Review: Validate findings with different agent perspectives
- Iterate: Loop back to research with refined focus areas
Output Requirements:
- Record entire process and final analysis in separate documentation folder
- Never modify existing documents during research phase
- Reference exact code locations without copying code snippets
- Maintain research trail for future reference and validation
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.
- 4d ago First seen · 54 lines · 0 tokens per session scan A 84fc9d3aae9f
8-deep-research is a command published in the GitHub repository clchinkc/document-mcp (0 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 502 tokens. 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 commands, from other repositories
OPSX: Propose
Propose a new change - create it and generate all artifacts in one step.
compile
Compile a FIBER decision context (world + query) and report the oracle verdict, omission accounting, and certificate digest faithfully.
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.