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.
git clone --depth 1 https://github.com/solanabr/solana-ai-kitWrote 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/commands/solanabr/solana-ai-kit/test-ts)<a href="https://agentmods.dev/commands/solanabr/solana-ai-kit/test-ts"><img src="https://agentmods.dev/badge/commands/solanabr/solana-ai-kit/test-ts/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/commands/solanabr/solana-ai-kit/test-ts"><img src="https://agentmods.dev/badge/commands/solanabr/solana-ai-kit/test-ts.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 | $0.00017 | $0.00960 |
| Opus 5.5 | $0.00007 | $0.00384 |
| Sonnet 5.5 | $0.00003 | $0.00192 |
| Haiku 4.5 | $0.00002 | $0.00096 |
Grade A, and why
test-ts 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 25d 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 — 31 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Run the project's TypeScript suites and report each failure with its cause. $ARGUMENTS narrows the run (a file, test name pattern, or workspace package); empty means everything.
Harness setup (Kit LiteSVM plugin, embedded Surfpool under vitest): testing.md. Client and wallet patterns: frontend.md.
Steps
- If program code changed, rebuild it (
NO_DNA=1 anchor build); if instructions or accounts changed, regenerate the client with/generate-idl-client. A stale IDL or client fails as discriminator or account-count errors. - Run the suite that fits:
- Anchor TS tests (
tests/*.ts). Anchor 1.x scaffolds them only withanchor init --test-template mocha; its default template is Rust LiteSVM (see/test-rust).NO_DNA=1 anchor testbuilds, starts Surfpool, deploys, and runs[scripts] testfrom Anchor.toml. - One test at a time: keep a surfnet up (
anchor test --detachoranchor localnet), thenanchor run test -- --grep <pattern>(-tfor jest; keep the pattern free of spaces).anchor runexports theANCHOR_PROVIDER_URLandANCHOR_WALLETthatAnchorProvider.env()reads. Typing the wallet path yourself trips the kit's secrets hook, which blocks commands naming~/.config/solana/id.json. - The Anchor TS package is
@anchor-lang/core. Imports from@coral-xyz/anchor, including deepdist/cjs/idlimports, are pre-1.0 and need updating. - Kit program tests:
@solana/kit-plugin-litesvmfor in-process tests,@solana/surfpool/kitfor an embedded surfnet per suite withclient.cheatcodes. Run Surfpool-backed files serially (vitestfileParallelism: falseor a separate config). - Frontend: the package's
testscript (vitest or jest). E2E:npx playwright test, or drive the running app through the Playwright MCP if it is configured (/setup-mcpadds it). Wallet extensions do not load in headless browsers; register a test Wallet Standard wallet backed by a local keypair behind a test-only flag, against localnet or devnet.
- Anchor TS tests (
- Rerun only the failing file or test name.
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.
- 25d ago Changed · -374 lines · +5 tokens per session d52af3638aac
- 26d ago Changed 065d19e7ccfc
- 1mo ago First seen · 405 lines · 12 tokens per session scan A b33d18c46ea4
test-ts is a command published in the GitHub repository solanabr/solana-ai-kit (104 stars, last pushed 26d ago), licensed MIT. It adds 17 tokens to every session and 960 once invoked, about $0.0001 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 2026-08-30.
Other commands, from other repositories
apex
APEX Methodology - The systematic Analyze-Plan-Execute-eLicit-eXamine approach for intelligent development. Reduces hallucination and defect risk through mandatory parallel research, self-review, and validation gates.
test
Test commit. Use for add tests, update tests, test coverage, unit test, spec.
plan-feature
Production-grade feature planning with dual-AI validation (Claude + Antigravity/Gemini 3 via agy).
generate-tests
Begin by outputting: [ Manta — Generate Tests ].
write-tests
Write tests for: $ARGUMENTS.
plan-refactor
Plan a refactor as a sequence of safe verified steps, with tests established before anything moves.