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 skills/quantumentangled-dev/ai-docs-plugin/askuser-protocolnpx skills add quantumentangled-dev/ai-docs-plugin --skill askuser-protocolgit clone --depth 1 https://github.com/quantumentangled-dev/ai-docs-pluginWhat 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 | $0.00041 | $0.00418 |
| Opus 5 | $0.00020 | $0.00209 |
| Sonnet 5 | $0.00008 | $0.00084 |
| Haiku 4.5 | $0.00004 | $0.00042 |
Grade A, and why
askuser-protocol 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 yesterday.
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.
What it actually says
askuser-protocol
Hard rules (subagent)
- MUST NOT call
AskUserQuestion. - MUST NOT emit prose questions directed at the user.
- MUST NOT embed
AskUserQuestioninvocation syntax in the response body. - MUST surface a Blocker Report when required input is missing from the dispatch prompt.
Blocker Report format
Final response shape when missing input:
## Missing Inputs
| Parameter | Type | Expected Values | Rationale |
|-----------|------|-----------------|-----------|
| <name> | <type> | <values> | <why needed> |
**Blocker**: Cannot proceed without the above. Re-delegate with these values injected.
A Blocker Report is NOT a success and NOT a Refusal. It's a distinct output the orchestrator routes specifically.
Output shapes (final message must be exactly one)
- Success — opens with the success-line declared by the subagent's own contract (e.g.
Published:,Unpublished:,Proposal:). - Refusal — opens with
Refusal:+ brief reason. Operation will not be retried with the same inputs. - Blocker Report — opens with
## Missing Inputs. Orchestrator collects values + re-dispatches. - Tool error verbatim — wrapped script's stderr passed through. Orchestrator treats as Refusal unless context suggests retry.
Never emit a success opener when no operation ran. Never embed a user-directed question — surface a Blocker Report instead.
Pattern informed by MoAI-ADK (Apache 2.0). Paraphrased; no verbatim text reuse.
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.
- yesterday First seen · 44 lines · 41 tokens per session scan A a92089b7f3cb
askuser-protocol is a skill published in the GitHub repository quantumentangled-dev/ai-docs-plugin (6 stars, last pushed 3mo ago), licensed MIT. It adds 41 tokens to every session and 418 once invoked, about $0.0002 per session on Opus 5. 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 skills, from other repositories
weekly-digests
Generate a serial week-by-week narrative digest of a project's full claude-mem timeline. Splits the timeline into per-ISO-week files, then runs one consecutive subagent per week — each receiving the prior week's carry-forward block — to produce one chapter per ISO week of data. Use when asked for "weekly digests"…
agentmail
Use when an agent needs AgentMail CLI email inboxes.
skill-template
Template for creating new Agent Skills for context engineering. Use this template when adding new skills to the collection.
Agent Development
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development…
skill-creator
Scaffold a new yoyo skill when a human or community issue asks for one ("add a skill for X", "create a skill that does Y"). Generates correct frontmatter, validates, writes to disk.
subagent-delegation
Canonical protocol for delegating GSD work to native Antigravity subagents — when to delegate, how to invoke, workspace isolation modes, and the inline fallback for older IDE versions.