What is aptu-coder src.instructions.md?

A set of coding rules for the aptu-coder project’s Rust source code. It covers the rmcp tool API, error handling, logging, tracing, and dependency changes.

Reviewing or implementing rmcp tools, handling errors, adding tracing to I/O and parsing code, checking dependency changes, and enforcing project conventions.

It catches project-specific mistakes before they become review or runtime problems. The rules make tool responses, failures, observability, and scope consistent.

aptu-coder src.instructions.md — Instructions file by clouatre-labs

Install

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.

agentmods

npx agentmods add instructions/clouatre-labs/aptu-coder/src

Clone the repo

git clone --depth 1 https://github.com/clouatre-labs/aptu-coder

Made for: GitHub Copilot.

Per session 466 This file is loaded in full into every session.

When invoked 466 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00466	$0.00466
Opus 5	$0.00233	$0.00233
Sonnet 5	$0.00093	$0.00093
Haiku 4.5	$0.00047	$0.00047

Measured 2d ago against content hash 3822855c023d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

aptu-coder src.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.

.github/instructions/src.instructions.md · 39 lines

What it actually says

rmcp API correctness

Do not rely on training data for rmcp APIs -- verify against Cargo.lock and src/lib.rs.

Every #[tool(...)] attribute requires output_schema = schema_for_type::<T>(). Titles go in annotations(title = "..."), not as a top-level title = "..." field. Flag tools missing output_schema.
Tool methods must take a RequestContext<RoleServer> as the second parameter after &self. Flag methods that omit it or use a different type.
#[tool_router] and #[tool_handler] go on separate impl blocks. Flag if either appears on the wrong block.
Every CallToolResult::success(...) must be chained with .with_meta(...). Flag success responses missing it.

Error handling

Use thiserror for error types (library crate). Flag use of anyhow in src/.
Prefer ? over .unwrap() or .expect() in non-test code. Flag .unwrap() in src/ unless a comment explains why it cannot fail.

Observability

Flag async fn that perform I/O or tree-sitter parsing without #[instrument].
Flag direct eprintln! or println! in src/.

Scope

Flag any new dependency in Cargo.toml not justified in the PR description.
Flag unsafe blocks unconditionally.
Flag changes to files outside the scope described in the PR description.

Tool parameter invariants

Behavioral contracts enforced at runtime -- must be preserved across refactors:

summary=true and cursor together must return INVALID_PARAMS. Flag any change that weakens this check.
impl_only=true on a non-Rust directory must return INVALID_PARAMS. Flag changes that allow it to silently no-op instead of erroring.
analyze_module accepts path only. Flag any PR that adds pagination, summary, force, or verbose to its parameter type.

Changes

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 · 39 lines · 466 tokens per session scan A 3822855c023d

Subscribe to this mod's changes

aptu-coder src.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 466 tokens to every session, about $0.0023 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.

Languages Rust ai aptu ast call-graph code-analysis developer-tools

arbor copilot-instructions.md

Copilot instructions for getArbor-dev/arbor: Ensure that the previous step has been marked as completed. Call project setup tool with projectType parameter. Run scaffolding command to create project files and folders. Use '.' as the working directory. If no appropriate projectType is available, search documentation…

getArbor-dev/arbor · 1,131 tokens

aptu-coder src.instructions.md

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

rmcp API correctness

Error handling

Observability

Scope

Tool parameter invariants

What this file has done since we first saw it

Other instructions, from other repositories

arbor copilot-instructions.md

codeweave-mcp CLAUDE.md

codexray CLAUDE.md

graphify AGENTS.md

codeseek CLAUDE.md

arbor CLAUDE.md