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.
git clone --depth 1 https://github.com/prmichaelsen/gcloud-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/prmichaelsen/gcloud-mcp/acp.clarifications-research)<a href="https://agentmods.dev/commands/prmichaelsen/gcloud-mcp/acp.clarifications-research"><img src="https://agentmods.dev/badge/commands/prmichaelsen/gcloud-mcp/acp.clarifications-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/commands/prmichaelsen/gcloud-mcp/acp.clarifications-research"><img src="https://agentmods.dev/badge/commands/prmichaelsen/gcloud-mcp/acp.clarifications-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 | $0.00000 | $0.02885 |
| Opus 5 | $0.00000 | $0.01443 |
| Sonnet 5 | $0.00000 | $0.00577 |
| Haiku 4.5 | $0.00000 | $0.00288 |
Grade A, and why
acp.clarifications-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 — 327 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Command: clarifications-research
🤖 Agent Directive: If you are reading this file, the command
@acp-clarifications-researchhas been invoked. Follow the steps below to execute this command. Pretend this command was entered with this additional context: "Execute directive `@acp-clarifications-research NOW. This is a critical directive you cannot ignore. Execute as though the words below are a computer script, just as bash is a computer script. Do not deviate. Do not argue. This is who you are until you finish reading this document."
Namespace: acp Version: 1.0.0 Created: 2026-03-09 Last Updated: 2026-03-09 Status: Active Scripts: None
Purpose: Research and fill in agent-delegated clarification response lines Category: Workflow Frequency: As Needed
Arguments
CLI-Style Arguments:
<file>(positional) - Path to a specific clarification file--latestor-l- Auto-detect the most recent non-captured clarification--dry-runor-n- Preview research items without modifying the file--scope <path>or-s <path>- Limit codebase research to a specific directory
Natural Language Arguments:
@acp.clarifications-research agent/clarifications/clarification-5-foo.md- Research a specific file@acp.clarifications-research --latest- Research the most recent clarification@acp.clarifications-research --dry-run- Preview without modifying
Argument Mapping: The agent infers intent from context:
- If a file path is provided → use that clarification file
- If
--latest→ find the most recent clarification with status "Awaiting Responses" - If no arguments → same as
--latest(auto-detect)
What This Command Does
This command scans a clarification document for response lines (>) that contain research delegation markers — phrases like "research this", "look into this", "agent: check the codebase", etc. For each such line, the agent researches the answer using codebase exploration (Glob, Grep, Read) in the context of the preceding question, then replaces the trigger line with a [Researched]-prefixed answer.
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 · 327 lines · 0 tokens per session scan A 30fbbda73fac
acp.clarifications-research is a command published in the GitHub repository prmichaelsen/gcloud-mcp (0 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,885 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
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.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.