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/1-askgit clone --depth 1 https://github.com/clchinkc/document-mcpWhat 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 | $0.00757 |
| Opus 5 | $0.00000 | $0.00378 |
| Sonnet 5 | $0.00000 | $0.00151 |
| Haiku 4.5 | $0.00000 | $0.00076 |
Grade A, and why
1-ask 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 2d 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Requirements Discovery and Clarification
Workflow Stage: Requirements Discovery
Engage with the user to understand their feature idea through targeted questions and discussion, building context for subsequent specification generation.
This workflow focuses on exploring and clarifying the user's needs through conversational inquiry rather than formal documentation.
Constraints:
- The model MUST engage in a conversational exploration of the user's feature idea or problem
- The model MUST ask targeted, relevant questions based on the initial description
- The model SHOULD focus on understanding:
- The core problem or need being addressed
- Who will use the feature (target users/roles)
- The expected scale and scope
- Integration requirements with existing systems
- Key functional requirements
- Non-functional requirements (performance, security, scalability)
- Any specific constraints or dependencies
- The model MUST adapt its questions based on the user's responses
- The model SHOULD identify gaps in understanding and probe deeper when necessary
- The model MUST NOT create any specification files during this phase
- The model MUST maintain context from all responses for future reference
- The model SHOULD summarize key findings periodically to confirm understanding
- The model MAY suggest considerations the user might not have thought of
- The model SHOULD explore edge cases and potential challenges
- The model MUST prepare the groundwork for formal specification generation
Question Categories
Initial Understanding
- What is the main problem you're trying to solve?
- Who are the primary users of this feature/system?
- What is the expected scale (number of users, data volume, etc.)?
- What are the key outcomes you want to achieve?
Functional Requirements
- What are the core functionalities needed?
- How do users currently handle this task (if applicable)?
- What are the must-have vs nice-to-have features?
- Are there any specific workflows or processes to support?
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.
- 2d ago First seen · 86 lines · 0 tokens per session scan A 1117be960b38
1-ask 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 757 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
methodology
View your cognitive methodology profile and reasoning patterns.
release
Comprehensive workflow for releasing a new version of the VectorMCP Ruby gem following best practices.
compile
Compile a FIBER decision context (world + query) and report the oracle verdict, omission accounting, and certificate digest faithfully.
safety-check
Verify the EA1 safety gate blocks all destructive actions on a page.
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.