claude-sdk-rs: Instructions file for Claude Code

CLAUDE.md

claude-sdk-rs CLAUDE.md is an instructions file for Claude Code from bredmond1019/claude-sdk-rs. It costs 2,817 tokens per session, scanned A, original, Apache-2.0.

A set of Claude Code instructions for a Rust software-development project. It explains project context, planning files, repository boundaries, known issues, and build, test, and run procedures.

In plain words
What is it for?
It helps the assistant work within the repository's planning, documentation, and testing process.
Why use it?
It prevents the coding assistant from overlooking project rules, symlink details, or where planning changes belong.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

This is bredmond1019/claude-sdk-rs's own configuration. It tells Claude Code how to work on claude-sdk-rs itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything claude-sdk-rs configures →

Reuse

Borrowing it

Nothing to install: this file belongs to bredmond1019/claude-sdk-rs. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/bredmond1019/claude-sdk-rs/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/bredmond1019/claude-sdk-rs

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for claude-sdk-rs CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/bredmond1019/claude-sdk-rs/claude-md/github.svg)](https://agentmods.dev/instructions/bredmond1019/claude-sdk-rs/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/bredmond1019/claude-sdk-rs/claude-md"><img src="https://agentmods.dev/badge/instructions/bredmond1019/claude-sdk-rs/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for claude-sdk-rs CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/bredmond1019/claude-sdk-rs/claude-md"><img src="https://agentmods.dev/badge/instructions/bredmond1019/claude-sdk-rs/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,817 This file is loaded in full into every session.
When invoked 2,817 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.02817 $0.02817
Opus 5.5 $0.01127 $0.01127
Sonnet 5.5 $0.00563 $0.00563
Haiku 4.5 $0.00282 $0.00282

Measured 11d ago against content hash f683fa6d8a54, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

claude-sdk-rs CLAUDE.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 11d 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.

CLAUDE.md · 203 lines

How it starts

The opening of the file, as written. The whole thing — 203 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — claude-code-rs

A lean async Rust SDK that runs Claude Code as a subprocess on Brandon's flat-rate subscription (not API credits).

Before you start

  • Strategic context: planning/context.md (read first) → planning/status.md (current state)
  • Symlink warning: the planning/ directory is actually a local symlink pointing to the company brain repo's _planning/ vault (e.g. core/_planning/claude-code-rs/). The brain repo is responsible for tracking all planning files under Git. Do not track planning/ in this project's public Git repository (it is gitignored).
  • Symlink traps: rg/grep/find are symlink-blind by default — a search that must include planning/ content needs -L/--follow. git mv fails through the symlink face ("source directory is empty") — move planning files via the real vault path (.../_planning/<slug>/...), never via planning/.... Planning changes are committed in the brain repo (agentic-portfolio) with an explicit pathspec, never in this repo.
  • Plan: planning/master-plan.md — the phase/block sequence
  • Pipeline config: planning/harness.json — the validation commands + UI-test config the SDLC engines run (see planning/harness.examples.md for ready-made stack profiles)
  • Decisions log: planning/decisions/ (start at planning/decisions/index.md) — check before relitigating any settled choice

Standing rules

  1. Every block/task ships with tests covering its core functionality. No exceptions.
  2. Every new .md under docs/ or planning/ must open with OKF YAML frontmatter. Required fields: type (e.g. Decision, Index, Reference, Plan, Log, ProjectStatus, LocalContext, Guide); title (human-readable); description (one-line summary for embedding). Optional but strongly encouraged: doc_id (kebab-case stable id, defaults to filename stem); layer (list from closed vocab: factory · brain · engine · console · surface · infra · business · content · meta); project (the project's own slug — see docs/okf-frontmatter.md in the company brain for the controlled vocabulary); status (active · draft · deprecated · superseded · archived); keywords (3–7 topic terms); related (list of doc_ids). Canonical guide: agentic-portfolio/docs/okf-frontmatter.md (governed by brain decision D27). Adding a file to a directory requires updating that directory's index.md — propagate up the chain as needed.
  3. Sequence, not calendar — work the order in master-plan.md; pick up where you left off.
  4. Decisions are append-only — never edit a settled decision; supersede it with a new atomic file in planning/decisions/ and link back.
  5. Verified identity / handles: none — treat these as the only authoritative identities/URLs; flag any other handle or profile link as unverified before publishing it.
  6. Never git push this repo directly from inside it. engine-rs path-depends on this repo, and every Rust repo's CI clones its sibling path-deps at their unpinned default branch — pushing out of order breaks a sibling's CI on code that was actually fine (the 2026-08-18 mev/bastion outage is the canonical example of this failure mode). Route every push through the company-brain's agentic-portfolio/scripts/git_push.sh --all, which pushes the whole fleet in dependency order and skips a repo flagged ci-blocked (a Cargo dependency is red on GitHub with nothing queued to fix it). Branching, committing, and opening/reviewing/merging PRs to main locally are all fine from inside this repo — only the final git push of main to origin must go through that script.

Read the full file on GitHub · 203 lines

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.

  1. 11d ago First seen · 203 lines · 2,817 tokens per session scan A f683fa6d8a54

Subscribe to this mod's changes

claude-sdk-rs CLAUDE.md is an instructions file published in the GitHub repository bredmond1019/claude-sdk-rs (23 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 2,817 tokens to every session, about $0.0113 per session on Opus 5.5. 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 2026-10-26.

Related

claude-sdk-rs CLAUDE.md compared with instructions from other repositories

claude-sdk-rs CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
claude-sdk-rs CLAUDE.mdbredmond1019/claude-sdk-rsInstructions file231mo agoApache-2.0A2,817Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode