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 skills add allemaar/open-skills --skill ask-gategit clone --depth 1 https://github.com/allemaar/open-skillsWrote 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/skills/allemaar/open-skills/ask-gate)<a href="https://agentmods.dev/skills/allemaar/open-skills/ask-gate"><img src="https://agentmods.dev/badge/skills/allemaar/open-skills/ask-gate/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/skills/allemaar/open-skills/ask-gate"><img src="https://agentmods.dev/badge/skills/allemaar/open-skills/ask-gate.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 | $0.00118 | $0.01692 |
| Opus 5 | $0.00059 | $0.00846 |
| Sonnet 5 | $0.00024 | $0.00338 |
| Haiku 4.5 | $0.00012 | $0.00169 |
Grade A, and why
ask-gate 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 10d 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/ask-gate
Ask-Gate (AGP) governs the moment just before a handler-facing question. Asking is cheap to type and expensive to waste — a question the agent could have answered itself is a nag, and a high-stakes question asked with the wrong options or framing burns the one interaction that mattered. AGP makes AskUserQuestion a deliberate, quality-gated reflex instead of a casual reach: triage whether to ask at all, ask routine questions directly after a quick checklist, and escalate the questions that actually matter through /insight-critique then /insight-assess before surfacing them.
AGP is invoked two ways: automatically, as the standard reflex before any AskUserQuestion (it can fire inside COP's surface step, inside NSP's surface step, or standalone); or directly, as /ask-gate to quality-gate a specific pending question.
Structured execution spec:
protocol.yon. Read it for the canonical rules and step sequence; this file is explanation. The two must stay in sync — if you edit one, update the other and refresh the@STAMPdate.
The protocol — three steps
1. Triage (anti-nag)
A question is the handler's to answer only if it cannot be resolved from the request, the code, or sensible defaults. If it can be resolved, resolve it, state the choice you made, and do not ask. Asking a resolvable question is the single most common nag failure — this gate exists to kill it. This mirrors COP's step-1 anti-nag triage; if nothing genuinely needs the handler, AGP surfaces nothing.
2. Classify stakes
If a question is warranted, classify it:
- Routine — low-stakes, reversible, one obvious framing (a preference, an NSP "which next skill?", a yes/no with a clear default). → Routine path (3a).
- High-stakes — architecturally load-bearing, hard to reverse, commits resources or time, or 3+ viable options where the framing itself is uncertain, or the answer shapes a plan/roadmap. → High-stakes path (3b).
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago First seen · 96 lines · 118 tokens per session scan A 17bb88266721
ask-gate is a skill published in the GitHub repository allemaar/open-skills (14 stars, last pushed 23d ago), licensed Apache-2.0. It adds 118 tokens to every session and 1,692 once invoked, about $0.0006 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 2026-08-30.
Other skills, from other repositories
polis-protocol
Set up and run a self-improving, multi-vendor AI agent team with the Polis Protocol — a markdown polis/ folder where each agent is a citizen with a capability card, tasks are contracts routed to whoever has the best track record by a learning router, settled work files lessons that compound into team memory, and…
media
Skill "media" from ymxlx/polis-protocol, covering polis protocol: a self-optimizing city of agents, the core idea, when this skill is active, structure of a polis and the first thing to do every session.
_data
Skill "_data" from ymxlx/polis-protocol, covering polis protocol: a self-optimizing city of agents, the core idea, when this skill is active, structure of a polis and the first thing to do every session.
subagent-driven-development
Execute plans via delegatetask subagents (2-stage review).
mcporter
List, auth, and call MCP servers/tools from the terminal.
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.