Borrowing it
Nothing to install: this file belongs to alex-alecu/garden-desk. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/alex-alecu/garden-desk/main/.agents/skills/garden-desk-verify-change/SKILL.mdgit clone --depth 1 https://github.com/alex-alecu/garden-deskWrote 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/alex-alecu/garden-desk/garden-desk-verify-change)<a href="https://agentmods.dev/skills/alex-alecu/garden-desk/garden-desk-verify-change"><img src="https://agentmods.dev/badge/skills/alex-alecu/garden-desk/garden-desk-verify-change/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/alex-alecu/garden-desk/garden-desk-verify-change"><img src="https://agentmods.dev/badge/skills/alex-alecu/garden-desk/garden-desk-verify-change.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 | $0.00040 | $0.00361 |
| Opus 5 | $0.00020 | $0.00180 |
| Sonnet 5 | $0.00008 | $0.00072 |
| Haiku 4.5 | $0.00004 | $0.00036 |
Grade A, and why
garden-desk-verify-change 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 8d 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.
What it actually says
Verify A Garden Desk Change
Top priority: run the smallest complete command set that proves the changed behavior. A general instruction to run a full command does not mean the largest repository gate.
- Inspect the complete diff and changed-file list, including unrelated pre-existing changes.
- For documentation or instructions only, inspect links and command names and run
git diff --check. Run no product tests. - For a focused source change, run
pnpm lint,pnpm typecheck, and the one focused test required by the Test Rule, if any. For a platform boundary, usepnpm test:platform:gate. For an M2 native boundary, usepnpm test:native:m2. - Run
pnpm verifyonly for a native helper, build script, or packaged runtime. Do not duplicate commands that it includes. Leave the fullpnpm testsuite to CI unless the owner explicitly requests a local run. - Run a real model, physical microVM, golden task, or milestone gate only as a last resort and only with explicit owner approval under AGENTS.md. A retry needs new approval.
- Record exact commands and outcomes. Never report a skipped, unavailable, or unapproved check as a pass.
Produce:
## Verification Report
- Changed surfaces:
- Commands passed:
- Commands failed:
- Not run and why:
- Conclusion: ready | not ready | blocked
Do not fix failures unless the user asked for a fix.
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.
- 8d ago First seen · 30 lines · 40 tokens per session scan A 8281ae345048
garden-desk-verify-change is a skill published in the GitHub repository alex-alecu/garden-desk (6 stars, last pushed yesterday), licensed Apache-2.0. It adds 40 tokens to every session and 361 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 2026-09-04.
Other skills, from other repositories
verify
Confirm a change works before claiming completion — runs a tiered evidence ladder (existing tests → build → narrow commands → manual) and reports only what was actually proven, never bluffs completion.
test-driven-development
Use when implementing any feature or bugfix, before writing implementation code.
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
skill-authoring
Use when creating new skills, editing existing skills, or verifying skills work before deployment. Applies TDD methodology to skill documentation.
systematic-debugging
4-phase root cause debugging: understand bugs before fixing.
react-patterns
React 18/19 patterns including hooks discipline, server/client component boundaries, Suspense + error boundaries, form actions, data fetching, state management decision trees, and accessibility-first composition. Use when writing or reviewing React components.