Borrowing it
Nothing to install: this file belongs to waanvar/samong. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/waanvar/samong/main/CLAUDE.mdgit clone --depth 1 https://github.com/waanvar/samongWrote 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/waanvar/samong/claude-md)<a href="https://agentmods.dev/instructions/waanvar/samong/claude-md"><img src="https://agentmods.dev/badge/instructions/waanvar/samong/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.
<a href="https://agentmods.dev/instructions/waanvar/samong/claude-md"><img src="https://agentmods.dev/badge/instructions/waanvar/samong/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00695 | $0.00695 |
| Opus 5 | $0.00347 | $0.00347 |
| Sonnet 5 | $0.00139 | $0.00139 |
| Haiku 4.5 | $0.00069 | $0.00069 |
Grade A, and why
samong 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 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.
How it starts
The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Samong — instructions for Claude Code
Read CONTRIBUTING.md first; it is the contract for what gets merged. This file
only adds what an agent cannot infer from the tree.
Before you finish a change
cd web && npm run build && cd .. # the UI is embedded at compile time
cargo test --all --locked
cargo clippy --all --all-targets --locked -- -D warnings
cargo fmt --all -- --check
All four must pass before you open a pull request. --locked everywhere, on
purpose: CI judges the dependency set that ships, not whatever resolved newest
today. Toolchain is Rust 1.88 (rust-version in Cargo.toml) and Node 22.
The semantic feature is off by default and no release binary carries it, so a
plain cargo test never compiles it. If you touched anything under it:
cargo test --features semantic --locked
cargo clippy --features semantic --all-targets --locked -- -D warnings
Do not download the embedding model in a sandbox — it is 465 MB and CI deliberately stops short of it.
Traps this project has actually fallen into
- The web UI is baked into the binary. Editing
web/and rebuilding only the crate keeps serving the old interface.npm run buildfirst, thencargo install --path . --forceif you are testing the binary by hand. - Never touch the real registry at
~/.config/samong. Tests fought over redb's lock in parallel and modified vaults people were using. PointSAMONG_CONFIG_DIRat a temporary directory. - Do not assert on wall-clock time. Assert what the feature promises. Timing assertions turned CI red for three pushes and said nothing about the bug.
- Case-insensitive filesystems.
Samong.exeonce overwrotesamong.exe. Anything that builds a path or filename across OSes needs a test that says so. - A command that reports success while doing nothing is the defect.
samong updatedid exactly that through five releases. Prefer a loud error over a quiet fallback, and add the test that would have caught it — not a test that merely exercises the new code. - New dependency → update
THIRD-PARTY.mdin the same commit.
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 · 65 lines · 695 tokens per session scan A 8d88a588cf58
samong CLAUDE.md is an instructions file published in the GitHub repository waanvar/samong (2 stars, last pushed today), licensed Apache-2.0. It adds 695 tokens to every session, about $0.0035 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 2026-09-08.
Other instructions, from other repositories
flow-like copilot-instructions.md
Copilot instructions for Rheosoph/flow-like, covering flow-like wasm node development — rust, project overview, build & test, architecture and pin types.
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).