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/jedarden/needle/claude-mdgit clone --depth 1 https://github.com/jedarden/NEEDLEWrote 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.
[](https://agentmods.dev/instructions/jedarden/needle/claude-md)<a href="https://agentmods.dev/instructions/jedarden/needle/claude-md"><img src="https://agentmods.dev/badge/instructions/jedarden/needle/claude-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.02220 | $0.02220 |
| Opus 5 | $0.01110 | $0.01110 |
| Sonnet 5 | $0.00444 | $0.00444 |
| Haiku 4.5 | $0.00222 | $0.00222 |
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 4d 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 — 211 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 bf CLI (bead-forge) to
select, claim, dispatch an AI agent, and handle outcomes.
MSRV
Minimum Supported Rust Version: 1.75 (2023-12-28).
Pinned in rust-toolchain.toml. Do not add dependencies that require a newer
Rust edition without updating MSRV and rust-toolchain.toml.
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()orexpect()in non-test code — use?withanyhow. - 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 warningsbefore committing. - Run
cargo fmtbefore committing.
Testing
- Unit tests live in
#[cfg(test)]modules in each source file. - Integration tests live in
tests/. - Do not use
tokio_test::block_on— use#[tokio::test]. - Test the public interface, not internals.
Test Isolation Policy
CRITICAL: Any integration test that spawns the compiled needle binary as a real subprocess via Command::new(CARGO_BIN_EXE_needle) MUST isolate both $HOME and the Explore strand's scan root.
The Explore strand (enabled by default via ExploreConfig::default_enabled()) scans workspace_root (defaulting to $HOME) for bead workspaces. Without isolation, a test's spawned binary will leak into the real user environment and scan real repos, contaminating both the test and production bead stores.
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.
- 4d ago First seen · 211 lines · 2,220 tokens per session scan A 5569131792b6
NEEDLE CLAUDE.md is an instructions file published in the GitHub repository jedarden/NEEDLE (20 stars, last pushed today), licensed MIT. It adds 2,220 tokens to every session, about $0.0111 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 2026-08-30.
Other instructions, from other repositories
harness-sdk AGENTS.md
AGENTS.md instructions for strands-agents/harness-sdk, covering agent development guide - strands agents monorepo, context, monorepo layout, where the "why" lives: team/ and writing code.
pipelex CLAUDE.md
Instructions for Pipelex/pipelex, covering pipelex coding rules, commands, linting, keyword-only arguments check and cleaning derived files.
matryca-plumber AGENTS.md
AGENTS.md instructions for MarcoPorcellato/matryca-plumber, covering agents.md — matryca plumber instruction router, audience map, instruction loading strategy, always-on working agreements and rule and skill routing.
pydantic-ai-todo CLAUDE.md
Instructions for vstorm-co/pydantic-ai-todo, covering claude.md, what this project is, commands, structure and core pattern.
matryca-plumber CLAUDE.md
Claude Code instructions for MarcoPorcellato/matryca-plumber, covering code audit — code intelligence, always do, never do, resources and cli.
tokenjam AGENTS.md
AGENTS.md instructions for Metabuilder-Labs/tokenjam, covering agents.md — tokenjam and quick rules for agents that don't read claude.md.