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 agents/weftcut/weftcut/testinggit clone --depth 1 https://github.com/WeftCut/WeftCutWhat 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 | $0.01467 |
| Opus 5 | $0.00000 | $0.00733 |
| Sonnet 5 | $0.00000 | $0.00293 |
| Haiku 4.5 | $0.00000 | $0.00147 |
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 yesterday.
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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Testing
Where WeftCut's tests live, why they're split the way they are, and how to run
each layer. There is no single tests/ directory — that's deliberate (see
Why not one directory). Tests are grouped by runner,
not scattered by neglect.
The layers
| Layer | Location | Runner | Command (cwd) |
|---|---|---|---|
| Unit (TS) | colocated next to source: apps/desktop/src/{renderer,main,shared}/**/*.{test,spec}.{ts,tsx} |
Vitest | npm test (repo root) · npm run test:watch (apps/desktop) |
| Build scripts | colocated: apps/desktop/scripts/*.test.mjs and apps/desktop/e2e/**/*.test.mjs (the fixture generator's own suite) |
node:test |
npm run test:scripts (repo root or apps/desktop) |
| Rust | native/** — inline #[cfg(test)] + native/tests/ |
cargo | see Rust (repo root) |
| E2E | apps/desktop/e2e/electron/*.spec.ts |
Playwright driving the real Electron app | npm run e2e (repo root or apps/desktop) · add -- --full for the @matrix tier |
| Mutation / PBT | mutates src/main/state/** (config: apps/desktop/stryker.config.mjs) |
StrykerJS (Vitest runner) | npm run pbt:stryker (apps/desktop) |
The apps/desktop unit script excludes **/*.browser.test.ts; there are none
today — it's a standing guard for a pattern that would need a browser runner.
Build-script tests are a separate command on purpose. vitest.config.ts
pins include to the three src/ roots, so scripts/*.test.mjs is invisible to
npm test — and they are node:test, not Vitest, so widening the glob would
not help. They are not folded into npm test because that script forwards
extra argv (npm test -- src/foo.test.ts), and a &&-chained second command
would swallow those args. CI runs both as adjacent steps on the Windows leg.
Note the quoted glob in the script: node --test expands it internally, so it
behaves the same under cmd.exe and sh — an unquoted glob or a bare directory
argument does not work.
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.
- yesterday First seen · 96 lines · 0 tokens per session scan A a470ece4dc39
testing is an agent published in the GitHub repository WeftCut/WeftCut (4 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,467 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 2026-08-31.
Other agents, from other repositories
dr-strategist
Direct-response strategist applying The Donahoe Method. Picks framework, audits copy, drives revisions to Method standards.
check
Code quality auditor for the Trellis channel runtime. Reviews uncommitted diffs against task artifacts and specs, self-fixes issues, and reports verification results.
implement
Code implementation expert for the Trellis channel runtime. Understands specs and task artifacts, then implements features. No git commit allowed.
openwiki-meeting-curator
Curates meeting transcript inbox items into proposal-safe OpenWiki pages, sources, people, organizations, decisions, and follow-ups.
openwiki-inbox-operator
Operates OpenWiki inbox queues, processes authorized inbox items, and routes meeting transcripts to proposal-safe curation workflows.
openwiki-editor
Creates proposal-safe OpenWiki page, source, and synthesis changes through configured OpenWiki MCP without mutating canonical files.