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/uhop/console-toolkit/write-testsnpx skills add uhop/console-toolkit --skill write-testsgit clone --depth 1 https://github.com/uhop/console-toolkitWhat 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 | $0.00031 | $0.00549 |
| Opus 5 | $0.00015 | $0.00275 |
| Sonnet 5 | $0.00006 | $0.00110 |
| Haiku 4.5 | $0.00003 | $0.00055 |
Grade A, and why
write-tests 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.
What it actually says
Write Tests
Write or update tests using the tape-six testing library.
Notes
tape-sixsupports ES modules (.js,.mjs,.ts,.mts) and CommonJS (.cjs,.cts).- TypeScript is supported natively — no transpilation needed (Node 22+, Deno, Bun run
.tsfiles directly). - The default
tape6runner uses worker threads for parallel execution.tape6-seqruns sequentially in-process — useful for debugging or when tests share state.
Steps
- Read the testing guide at
node_modules/tape-six/TESTING.mdfor API reference and patterns. - Identify the module or feature to test. Read its source code to understand the public API.
- Create or update the test file in
tests/test-<name>.js(or.tsfor TypeScript,.cjsfor CommonJS):- ESM (
.js):import test from 'tape-six'and import the module under test using the project's package name. - CJS (
.cjs):const {test} = require('tape-six')andconst {...} = require('my-package'). If the module under test uses top-levelawait,require()cannot load it — useawait import('my-package')inside async tests instead. - Write one top-level
test()per logical group. - Use embedded
await t.test()for sub-cases. - Use
t.beforeEach/t.afterEachfor shared setup/teardown. - Cover: normal operation, edge cases, error conditions.
- Use
t.equalfor primitives,t.deepEqualfor objects/arrays,t.throwsfor errors,await t.rejectsfor async errors. - All
msgarguments are optional but recommended for clarity.
- ESM (
- Run the new test file directly to verify:
node tests/test-<name>.js - Run the full test suite to check for regressions:
npm test- If debugging, use
npm run test:seq(runs sequentially, easier to trace issues). - To see which files are being run, add
--flags fo(overrides the default--flags FO).
- If debugging, use
- Report results and any failures.
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 · 34 lines · 31 tokens per session scan A 08973a0adf51
write-tests is a skill published in the GitHub repository uhop/console-toolkit (10 stars, last pushed 1mo ago), licensed BSD-3-Clause. It adds 31 tokens to every session and 549 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 2026-08-31.
Other skills, from other repositories
ui-ux-pro-max
Searchable UI/UX design databases: 50+ styles, 97 palettes, 57 font pairings, 99 UX rules, 25 chart types. CLI generates design systems from natural language. Data-driven complement to ui-design.
theme-component
Add complete theme support for one Recharts component. Invoke with the component name, for example theme-component XAxis.
typescript
Write strongly-typed TypeScript code in Recharts.
example
Create new example charts for Recharts documentation website.
investigate
Find root cause for a bug or an issue in Recharts and propose a solution.
mutation-testing
Run Stryker mutation tests on one or a few files and check the HTML report. Invoke when asked to run mutation tests, check mutation score/coverage, or find untested code paths.