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.clarification-capture)<a href="https://agentmods.dev/commands/prmichaelsen/gcloud-mcp/acp.clarification-capture"><img src="https://agentmods.dev/badge/commands/prmichaelsen/gcloud-mcp/acp.clarification-capture.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 | $0.00000 | $0.03071 |
| Opus 5 | $0.00000 | $0.01536 |
| Sonnet 5 | $0.00000 | $0.00614 |
| Haiku 4.5 | $0.00000 | $0.00307 |
Grade A, and why
acp.clarification-capture 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 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.
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 — 387 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Directive: clarification-capture
🤖 Agent Directive: This is a SHARED DIRECTIVE, not a user-invocable command. It is referenced by create commands (
design-create,task-create,pattern-create,command-create) to capture clarification decisions into entity documents.Do NOT invoke this directive directly. It is called internally by create commands when context capture is needed.
If you are a create command reading this file, follow the steps below to capture clarification context and generate a "Key Design Decisions" section for the entity being created.
Namespace: acp Version: 1.0.0 Created: 2026-03-04 Last Updated: 2026-03-04 Status: Active Scripts: None
Purpose: Capture decisions from ephemeral clarification files and chat context into permanent entity documents Category: Workflow (Internal Directive) Frequency: Called by create commands when context is available
Arguments
These arguments are passed through from the calling create command. The create command parses them and passes the relevant context to this directive.
CLI-Style Arguments:
| Argument | Alias | Behavior |
|---|---|---|
--from-clarification <file> |
--from-clar |
Capture from a specific clarification file |
--from-clarifications |
--from-clars |
Capture from all recent clarifications |
--from-chat-context |
--from-chat |
Capture decisions from chat conversation |
--from-context |
(none) | Shorthand for all sources (clarifications + chat) |
--include-clarifications |
(none) | Alias for --from-clars, enforces Key Design Decisions section |
Natural Language:
@acp.design-create --from-clar→ Capture from clarifications in session@acp.design-create --from-chat→ Capture from chat conversation@acp.design-create --from-context→ Capture from all sources@acp.design-create(no flags) → Auto-detect: equivalent to implicit--from-context
Default Behavior: When no --from-* flags are specified, the directive auto-detects clarifications and context in the current session. This is the common case.
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 · 387 lines · 0 tokens per session scan A 5aac56f14727
acp.clarification-capture 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 3,071 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.
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.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.