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/ronaknnathani/relay/implementnpx skills add ronaknnathani/relay --skill implementgit clone --depth 1 https://github.com/ronaknnathani/relayWhat 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 | $0.00067 | $0.01238 |
| Opus 5 | $0.00034 | $0.00619 |
| Sonnet 5 | $0.00013 | $0.00248 |
| Haiku 4.5 | $0.00007 | $0.00124 |
Grade A, and why
implement 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 2d 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Implement
Turn an implementation plan into working, tested code, one thin slice at a time, keeping the build and
existing tests green at every step. The bar: at any moment you could stop and the system is committable
— nothing half-built, nothing red. This phase consumes the artifact from plan; it does not design
the approach and does not open a PR. Decisions in the plan are settled — follow them; if one is
wrong or missing, stop and surface it rather than quietly inventing a different design.
Process
- Load the plan and review it critically. Read it end to end before touching code. If a task is ambiguous, a step is missing, or the approach looks wrong, raise it now — don't paper over a gap mid-implementation. Turn the plan's tasks into an ordered checklist of slices.
- Load coding guidance. Read the repo's
AGENTS.mdwhen present, then read global guidance from~/AGENTS.mdor~/.config/agents/AGENTS.mdwhen present. Repo guidance takes precedence over global guidance. Treat these files as implementation constraints for scope, style, tests, errors, comments, and workflow; if a plan conflicts with them, stop and surface the conflict before coding. - Learn the repo's own commands. Read the Makefile,
package.jsonscripts, or CI config to find the real build, typecheck, and test commands. Use those exact commands — never assume a toolchain the repo doesn't use. - Pick the smallest complete slice. A slice is the smallest change that is independently testable and leaves the system green — one task from the plan, often smaller. Do not start work on the default branch (main/master) without explicit consent.
- Tracer-bullet TDD — one test ↔ one cycle. Write a single failing test for the slice's next behavior, watch it fail (red), write the minimum code to pass it (green), then refactor if needed. Never write all the tests up front, and never refactor while a test is red — get to green first. For a bug, use the Prove-It pattern: first write the reproduction test that fails because of the bug, then fix the code so it passes.
- Verify the slice. Typecheck and run the targeted test files; confirm the slice's new test passes and no existing test regressed. The slice isn't done until the system is green again.
- Commit the green slice. Commit a coherent, working increment (follow the repo's
commitconventions). Keep the commit to this slice — don't fold in unrelated changes. - Next slice. Repeat 4–7 until every task in the plan is done. Hold scope: implement the plan, not adjacent improvements you notice along the way (note them for later).
- Final verification. Run the full build and test suite once. This is implement's own green
self-check, not the formal quality gate —
validateindependently runs the repo's full ordered gates and owns the authoritative go/no-go. Report what was built and which verifications passed. Stop here — implementation is complete; a separate workflow handles review and the PR.
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.
- 2d ago First seen · 75 lines · 67 tokens per session scan A 348f01cd8a87
implement is a skill published in the GitHub repository ronaknnathani/relay (3 stars, last pushed 5d ago), licensed MIT. It adds 67 tokens to every session and 1,238 once invoked, about $0.0003 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
winui-ui-testing
Automated UI testing for Windows desktop apps — generate a batch test script with the winapp ui UI Automation harness, run all tests in one pass, read results. Covers element assertions, interactions, value checking (TextBox, ComboBox, ToggleSwitch), keyboard shortcuts and typing (send-keys), hover, drag-and-drop…
pr-review
Multi-dimensional review of a PR or feature branch in microsoft/win-dev-skills. Activate on "review my PR / changes / branch", "vet before pushing", "PR review", "is this ready to merge". Fans out parallel sub-agents over skill content, the skill-vs-tool boundary (solution hierarchy), tool correctness…
winui-design
Use when designing, reviewing, or fixing WinUI 3: sample and control discovery with winapp find-ui, layout planning, control choice, Fluent Design alignment, Light/Dark/High Contrast theming, typography, spacing, brushes, accessibility, and XAML data-binding design. Load before authoring new XAML, reviewing UI PRs…
winui-dev-workflow
Build and run workflow for WinUI 3 apps with WinApp CLI 0.6+ — project creation with winapp new, project-mode winapp run, BuildAndRun.ps1 analyzer integration, crash diagnosis, and prerequisites. Use when creating, building, running, or fixing build errors in a WinUI 3 project.
winui-packaging
MSIX packaging, code signing, and distribution for WinUI 3 apps — build for release, certificate generation (winapp cert generate), certificate trust, code signing (winapp sign), self-contained deployment, CI/CD with GitHub Actions, and Microsoft Store submission. Use when preparing for release, creating MSIX…
winui-session-report
Analyze the current or a recent agent session (GitHub Copilot CLI or Claude Code) and generate a diagnostic report. Use only when the user explicitly asks for session feedback, agent debugging, or a review of what happened during a build session. Do not inspect session data automatically.