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 ronaknnathani/relay --skill clarifygit clone --depth 1 https://github.com/ronaknnathani/relayWrote 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/ronaknnathani/relay/clarify)<a href="https://agentmods.dev/skills/ronaknnathani/relay/clarify"><img src="https://agentmods.dev/badge/skills/ronaknnathani/relay/clarify/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/ronaknnathani/relay/clarify"><img src="https://agentmods.dev/badge/skills/ronaknnathani/relay/clarify.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 | $0.00102 | $0.01582 |
| Opus 5.5 | $0.00041 | $0.00633 |
| Sonnet 5.5 | $0.00020 | $0.00316 |
| Haiku 4.5 | $0.00010 | $0.00158 |
Grade A, and why
clarify 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 1mo 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Clarify
Produce a requirements + acceptance-criteria artifact that pins down what success looks like, so a
planner never has to guess. The bar: every requirement is measurable and every acceptance criterion is
checkable — you could hand the artifact to someone else and they'd build the right thing. This is a
peer phase to plan, not its parent: it grounds itself in the code via explore, then hands its
artifact to plan. It does not design the implementation and does not invoke plan.
Process
- Resolve from the codebase before asking. If a question's answer is discoverable in the code —
how a thing currently works, what the existing convention is, where an integration point lives —
call
explore(dispatch a sub-agent when available; otherwise do it inline) and find it. Only ask the user what you genuinely cannot determine. Bothering them with a discoverable fact erodes trust. - Form an explicit hypothesis of the whole task. Write down, for yourself, the outcome you think they want and the success criteria you'd accept. This is what you'll test against the stop condition — and it makes your questions sharper.
- Walk the coverage checklist to find the real gaps. Probe each dimension; skip the ones the code
or the request already settle:
- Edge cases — empty/missing/malformed input, boundaries, concurrency, large scale.
- Error handling — what should fail loudly, what should degrade, what the user sees on failure.
- Integration points — callers, callees, schemas, events, and contracts this touches.
- Scope boundaries — what is explicitly in vs. out; where this task ends.
- Design preferences — conventions, libraries, patterns the user wants honored or avoided.
- Backward compatibility — existing data, APIs, configs, behavior that must keep working.
- Performance needs — latency/throughput/memory targets, and on which path.
- Interview one question at a time. Asking several at once is bewildering — never dump a list. Each question carries your recommended default AND your current hypothesis, made visible:
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.
- 1mo ago First seen · 104 lines · 102 tokens per session scan A 2db0d08ecf16
clarify is a skill published in the GitHub repository ronaknnathani/relay (3 stars, last pushed 3d ago), licensed MIT. It adds 102 tokens to every session and 1,582 once invoked, about $0.0004 per session on Opus 5.5. 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
windbg-user-exception-triage
Use when a native C/C++ app, service, or user-mode driver host (including UMDF) crashes with a structured exception in a dump or WinDbg session, including native faults inside managed processes. Not for managed .NET exceptions, WinUI/XAML app errors, or kernel bugchecks.
windbg-user-heap-corruption-investigation
Use when an app, service, or user-mode driver host heap fails or Application Verifier detects corruption; inspect history and bounds. Not for kernel pool corruption or ordinary OOM.
windbg-kernel-lock-deadlock-triage
Use when kernel threads block on driver synchronization or Verifier reports a lock-order violation; build an owner/waiter graph. Not for treating every watchdog stop as a deadlock or listing every lock type with !locks.
windbg-user-mutex-held-across-co-await
Use when app, service, or user-mode driver C++ coroutine code holds a thread-affine lock across suspension and later hangs or fails. Not for all coroutine crashes or choosing lock performance.
aspire
Build, upgrade, and operate Aspire 13.5.x C# or TypeScript application hosts with the current CLI, AppHost, ServiceDefaults, integrations, dashboard, testing, MCP, and deployment patterns for distributed apps. USE FOR: Aspire.AppHost.Sdk, Aspire.Hosting., DistributedApplication.CreateBuilder, apphost.mts…
microsoft-agent-framework
Build .NET AI agents, harnesses, and multi-agent workflows with Microsoft Agent Framework using the right agent type, sessions, tools, workflows, hosting protocols, and enterprise guardrails. USE FOR: building or reviewing .NET code that uses Microsoft.Agents., Microsoft.Extensions.AI, AIAgent, HarnessAgent…