What is NEEDLE CLAUDE.md?

A set of instructions for NEEDLE, a Rust program that processes tracked work items by selecting them, assigning them to an AI assistant, and handling the results. It defines supported Rust versions, module relationships, coding rules, and testing expectations.

Use it when changing, testing, or reviewing NEEDLE, especially its command-line interface, worker modules, task storage, dispatching, and telemetry.

It keeps changes compatible with the project's older supported Rust version and avoids unsafe error handling. It also makes sure state changes are recorded and code follows the project's structure.

How jedarden/NEEDLE configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to jedarden/NEEDLE. 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/jedarden/NEEDLE/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/jedarden/NEEDLE

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/jedarden/needle/claude-md/github.svg)](https://agentmods.dev/instructions/jedarden/needle/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/jedarden/needle/claude-md"><img src="https://agentmods.dev/badge/instructions/jedarden/needle/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/jedarden/needle/claude-md"><img src="https://agentmods.dev/badge/instructions/jedarden/needle/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 3,197 This file is loaded in full into every session.

When invoked 3,197 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.

Model	Per session	Once invoked
Fable 5.1	$0.03197	$0.03197
Opus 5.5	$0.01279	$0.01279
Sonnet 5.5	$0.00639	$0.00639
Haiku 4.5	$0.00320	$0.00320

Measured 14d ago against content hash cf6213cd4568, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

NEEDLE 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 14d 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 · 262 lines

How it starts

The opening of the file, as written. The whole thing — 262 lines — stays where its author put it; the contents beside it link to each section on GitHub.

NEEDLE Project Conventions

Overview

NEEDLE (Navigates Every Enqueued Deliverable, Logs Effort) is a Rust bead worker binary. It automates bead processing by running the workspace's configured bead CLI (bead-rs bead, or bead-forge bf for explicitly bound legacy workspaces) to select, claim, dispatch an AI agent, and handle outcomes.

MSRV

Minimum Supported Rust Version: 1.95, which is the build toolchain pinned in rust-toolchain.toml (1.95.0).

The MSRV is the pin. Every needle-ci lane and every local build compiles with it, so ordinary CI enforces the declaration. scripts/check-msrv-drift.sh (run by the definition-of-done) fails when any workspace rust-version (Cargo.toml, crates/*/Cargo.toml) differs from the pin's major.minor. To adopt a newer compiler, bump the pin and every rust-version in one change.

History: the declaration read 1.75 from scaffolding until 2026-09-25, then 1.88, enforced by a separate verify-msrv needle-ci lane (bead needle-c63fbb7f). That lane was removed on 2026-10-03 (needle-9cdd39b6, needle-5e78a10d). It took 23 of a 37-minute median run, and NEEDLE is an application with no crate dependents, so a floor below the build toolchain protected only source builds on old compilers.

Module Dependency Graph

cli
 └─ worker
     ├─ strand ─ bead_store ─ types
     ├─ claim  ─ bead_store, telemetry, types
     ├─ prompt ─ config, types
     ├─ dispatch ─ config, telemetry, types
     ├─ outcome  ─ bead_store, config, telemetry, types
     ├─ health   ─ config, telemetry, types
     ├─ bead_store ─ types
     ├─ telemetry  ─ types
     └─ config     ─ types

Leaf modules (no internal deps): types, config, telemetry, bead_store, health.

Code Style

No unwrap() or expect() in non-test code — use ? with anyhow.
All public functions return Result<T>.
Telemetry must be emitted at every state transition and outcome.
Match arms must be exhaustive — no catch-all _ on outcome enums.
Run cargo clippy --all-targets -- -D warnings before committing.
Run cargo fmt before committing.

Read the full file on GitHub · 262 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.

14d ago Changed · +21 lines · +471 tokens per session cf6213cd4568
1mo ago Changed · -9 lines · -74 tokens per session 5a360eb4cac8
1mo ago Changed · +7 lines · +99 tokens per session 3e78742f215e
1mo ago Changed · +12 lines · +196 tokens per session 938319ea110f
1mo ago Changed · +20 lines · +285 tokens per session 93659e9ffa4b
2mo ago First seen · 211 lines · 2,220 tokens per session scan A 5569131792b6

Subscribe to this mod's changes

NEEDLE CLAUDE.md is an instructions file published in the GitHub repository jedarden/NEEDLE (33 stars, last pushed 2d ago), licensed MIT. It adds 3,197 tokens to every session, about $0.0128 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 2026-08-30.

Autonomous Agents LLM Orchestration agentic-ai ai-agents claude

NEEDLE CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
NEEDLE CLAUDE.mdjedarden/NEEDLE	Instructions file	33	2d ago	MIT	A	3,197	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

NEEDLE: Instructions file for Claude Code