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/phantom/phantom-connect-sdk/testingnpx skills add phantom/phantom-connect-sdk --skill testinggit clone --depth 1 https://github.com/phantom/phantom-connect-sdkWhat 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 | $0.00000 | $0.00689 |
| Opus 5 | $0.00000 | $0.00345 |
| Sonnet 5 | $0.00000 | $0.00138 |
| Haiku 4.5 | $0.00000 | $0.00069 |
Grade A, and why
testing 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: testing
Run the full quality pipeline from the repo root to verify the codebase is in a healthy state.
Arguments: [package-name] — optional. If provided, scope lint, type-check, and tests to that package only. If omitted, run everything across the full monorepo.
Pipeline steps
Run each step sequentially from the repo root. Stop and report on first failure — do not continue past a broken step.
Step 1 — Format (Prettier)
yarn prettier
Prettier rewrites files in place. After it runs, check git diff --stat to see which files were modified. If any files changed, report them — it means they were not formatted before. The step itself is not a failure (Prettier auto-fixes), but unformatted files should be flagged as a finding.
Step 2 — Build
# Full monorepo
yarn build
# Scoped to one package
yarn workspace @phantom/{package-name} build
A build failure means the output that consumers receive would be broken. Treat this as a blocker.
Step 3 — Type check
# Full monorepo
yarn check-types
# Scoped to one package
yarn workspace @phantom/{package-name} check-types
Type errors that slip past the build (e.g. when skipLibCheck is on) are caught here. Treat any error as a blocker.
Step 4 — Lint
# Full monorepo
yarn lint
# Scoped to one package
yarn workspace @phantom/{package-name} lint
Lint errors are blockers. Lint warnings should be reported but are not blockers.
Step 5 — Tests
# Full monorepo
yarn test
# Scoped to one package
yarn workspace @phantom/{package-name} test
Any failing test is a blocker. Report the test name, file, and failure message.
Output
After all steps complete, print a summary table:
| Step | Status | Notes |
|---|---|---|
| Prettier | ✓ / files changed / failed | List of reformatted files if any |
| Build | ✓ / failed | Error summary if failed |
| Type check | ✓ / failed | Error count and first few errors if failed |
| Lint | ✓ / warnings / failed | Warning count; errors if failed |
| Tests | ✓ / failed | Failing test names and messages if failed |
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 · 93 lines · 0 tokens per session scan A 59130863d5b6
testing is a skill published in the GitHub repository phantom/phantom-connect-sdk (159 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 689 tokens. 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…