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/clouatre-labs/aptu-coder/testsgit clone --depth 1 https://github.com/clouatre-labs/aptu-coderWhat 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 | $0.00417 | $0.00417 |
| Opus 5 | $0.00209 | $0.00209 |
| Sonnet 5 | $0.00083 | $0.00083 |
| Haiku 4.5 | $0.00042 | $0.00042 |
Grade A, and why
aptu-coder 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.
What it actually says
Structure
- One happy path and one edge case per distinct behavior. Flag test files where multiple tests exercise the same code path with only input variation (e.g., testing the same parse logic for five different languages when one representative suffices).
- Use AAA layout (Arrange, Act, Assert) with a blank line between each section. Flag tests that interleave setup and assertions.
- Use
TempDirfrom thetempfilecrate for filesystem fixtures. Flag tests that write to hardcoded paths, and avoid introducing new uses ofstd::env::temp_dir()directly.
Assertions
- Prefer specific assertions over boolean ones:
assert_eq!(output.functions.len(), 2)overassert!(output.functions.len() > 0). Flagassert!(x > 0)when an exact count is knowable from the fixture. - Assert on the property under test, not on implementation details. Flag assertions that check internal field names or intermediate struct layouts that are not part of the public API.
Async tests
- Use
#[tokio::test]for async test functions. Flag#[test]on functions that call.await.
Fixtures
- Inline fixture source as a raw string literal (
r#"..."#) for small cases. Flag test files that read fixture data from external files undertests/unless the fixture is reused across three or more test functions. - Shared fixtures belong in
tests/fixtures.rs. Flag duplicate fixture definitions across test files.
Scope
- Test files must not contain
#[allow(dead_code)]suppressing unused fixture helpers. Flag it: the helper should be removed or moved tofixtures.rs. - Do not introduce new
use aptu_coder::*glob imports in test files; if you touch an existing glob import, replace it with explicit imports so it is clear what is under test.
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 · 31 lines · 417 tokens per session scan A c83b564fd9c0
aptu-coder tests.instructions.md is an instructions file published in the GitHub repository clouatre-labs/aptu-coder (5 stars, last pushed 2d ago), licensed Apache-2.0. It adds 417 tokens to every session, about $0.0021 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
codeweave-mcp CLAUDE.md
Instructions for semihkayan/codeweave-mcp, covering claude.md, what this project is, build & run, architecture and layers.
codexray CLAUDE.md
Instructions for NeuralRays/codexray, covering codexray — ai agent instructions, workflow and key principle.
graphify AGENTS.md
AGENTS.md instructions for Graphify-Labs/graphify: This project has a graphify knowledge graph at graphify-out/.
codeseek CLAUDE.md
Instructions for CodeBendKit/codeseek, covering claude.md, build & test, enter rust project directory, build and run tests.
arbor CLAUDE.md
Claude Code instructions for getArbor-dev/arbor, covering claude.md, commands, build, test all crates and test single crate.
bonsai-ninja AGENTS.md
Instructions for gromhacks/bonsai-ninja, covering bonsai-ninja, map a codebase, optional explicit semantic sidecar prewarm, explicit spelling for default syntax/construct indexing and optional during active editing.