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 plangit 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/plan)<a href="https://agentmods.dev/skills/ronaknnathani/relay/plan"><img src="https://agentmods.dev/badge/skills/ronaknnathani/relay/plan/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/plan"><img src="https://agentmods.dev/badge/skills/ronaknnathani/relay/plan.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 | $0.00068 | $0.01349 |
| Opus 5.5 | $0.00027 | $0.00540 |
| Sonnet 5.5 | $0.00014 | $0.00270 |
| Haiku 4.5 | $0.00007 | $0.00135 |
Grade A, and why
plan 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan
Given a clarified requirements artifact, produce an implementation plan concrete enough that someone
with no prior context could execute it. The bar: exact file paths and names, one committed
architecture decision, and a phased build sequence implement consumes step by step — no abstract
advice, no "add appropriate error handling". This is a peer phase: it grounds itself in the code via
explore, picks ONE approach and commits, then hands a plan to implement. It does not clarify
requirements (that's clarify, upstream) and does not write production code (that's implement,
downstream). It does not invoke either.
Process
- Ground in the codebase first. Read the clarified artifact (
clarify's requirements + success criteria), then callexplore(dispatch a sub-agent when available; otherwise inline) and consume its essential-files list andfile:linecitations as the starting set for the existing patterns, conventions, and integration points this work touches. Cite each finding aspath/to/file.ext:line— the blueprint is built on what's actually there, not what you assume. - Decide the architecture and commit. Survey the realistic approaches, then pick ONE and write the decision plus a one-paragraph rationale grounded in the patterns from step 1. Do not hedge with "Option A or B" — a plan is a decision. Record approaches you rejected in one line each only if a reader would otherwise wonder why; don't relitigate.
- Choose the test seams up front. Pick where behavior gets verified, preferring a single highest seam (one integration/end-to-end point) over many low ones. Decide what's tested and what isn't, and capture it in an explicit Testing Decisions section. New behavior gets a test; a bug fix gets a test that fails without the fix.
- Design the components. For each unit of work name the file(s), its single responsibility, and its dependencies on other units. Split by responsibility, not by technical layer; files that change together live together; follow the established structure rather than restructuring it.
- Write the Implementation Map — every concrete create/modify action with its exact path:
Create src/x.ext/Modify src/y.ext:120-150/Test tests/x_test.ext. No file is named only in prose; if it changes, it's in the map. - Sequence the build into phases. Order the work so each phase produces something verifiable,
following dependency order (data/contracts → logic → wiring/config). Emit it as the Build
Sequence checklist below — this is the executable artifact
implementworks through. - Pin the critical details. State the concrete error-handling behavior, state/data shape, and
verification command for each phase. Add an Out of Scope section listing what this plan
deliberately does not touch, so
implementdoesn't wander. - Self-review with fresh eyes. Walk every Success criterion in the clarified artifact and point to the task that satisfies it — list and fix any gap. Scan for placeholders (TBD, TODO, "handle edge cases", a test step with no assertion) and remove them. Confirm names/signatures used in a later task match what an earlier task defines. Fix inline; don't re-review.
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 · 88 lines · 68 tokens per session scan A 4d5915923831
plan is a skill published in the GitHub repository ronaknnathani/relay (3 stars, last pushed 3d ago), licensed MIT. It adds 68 tokens to every session and 1,349 once invoked, about $0.0003 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…