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 instructions/jketreno/clare/testsgit clone --depth 1 https://github.com/jketreno/clareWhat 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 | $0.00747 | $0.00747 |
| Opus 5 | $0.00374 | $0.00374 |
| Sonnet 5 | $0.00149 | $0.00149 |
| Haiku 4.5 | $0.00075 | $0.00075 |
Grade A, and why
clare tests.instructions.md 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Testing Standards (CLARE — Assertive)
CLARE requires constraint tests, not confirmation tests. Every test file must enforce invariants — things that must always be true — not just describe what the current implementation does.
The Core Distinction
// ❌ Confirmation test — describes implementation, not invariant
it('returns the user', () => {
const user = getUser(1);
expect(user.id).toBe(1);
});
// ✅ Constraint test — enforces an invariant
it('always returns a user matching the requested ID', () => {
fc.assert(
fc.property(fc.integer({ min: 1, max: 10000 }), (id) => {
seedUser(id);
const user = getUser(id);
expect(user.id).toBe(id);
})
);
});
Rules for Every Test File
-
Name tests as invariants, not as implementations:
- ❌
'creates a user' - ✅
'never allows duplicate emails'
- ❌
-
Add at least one property-based test per critical module using
fast-check(JS) orhypothesis(Python) -
Architecture tests go in
tests/architecture/and run inverify-ci.sh; they must check structural constraints, not behavior:// Architecture test example test('all API endpoints have rate limiting', () => { const endpoints = loadEndpoints(); endpoints.forEach(ep => expect(ep).toHaveRateLimiting()); }); -
Schema-lock tests: For any external contract (API, event schema, proto), add a test that would fail if the schema changes unexpectedly:
test('User API response matches expected schema', () => { const response = getUser(seed.userId); expect(response).toMatchSnapshot(); // or use Zod schema assertion }); -
Test the test — After writing tests, delete the implementation and regenerate it with AI. If tests fail, they are working. If they pass, verify the constraints are strong enough.
Property-Based Testing Quick Reference
// fast-check (TypeScript/JavaScript)
import fc from 'fast-check';
test('never creates negative balances', () => {
fc.assert(
fc.property(
fc.integer({ min: 1, max: 10000 }),
fc.integer({ min: 1, max: 10000 }),
(initialBalance, deductAmount) => {
fc.pre(deductAmount <= initialBalance); // precondition
const result = deduct(initialBalance, deductAmount);
expect(result).toBeGreaterThanOrEqual(0);
}
)
);
});
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 · 95 lines · 747 tokens per session scan A 441a7298b310
clare tests.instructions.md is an instructions file published in the GitHub repository jketreno/clare (5 stars, last pushed 1mo ago), licensed MIT. It adds 747 tokens to every session, about $0.0037 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 instructions, from other repositories
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.