Borrowing it
Nothing to install: this file belongs to 24X7/riz. 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/24X7/riz/main/CLAUDE.mdgit clone --depth 1 https://github.com/24X7/rizWrote 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/24x7/riz/claude-md)<a href="https://agentmods.dev/instructions/24x7/riz/claude-md"><img src="https://agentmods.dev/badge/instructions/24x7/riz/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/24x7/riz/claude-md"><img src="https://agentmods.dev/badge/instructions/24x7/riz/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 | $0.01086 | $0.01086 |
| Opus 5.5 | $0.00434 | $0.00434 |
| Sonnet 5.5 | $0.00217 | $0.00217 |
| Haiku 4.5 | $0.00109 | $0.00109 |
Grade A, and why
riz 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 2mo 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
riz is a self-hosted AWS Lambda + API Gateway v2 runtime in one Rust binary: six runtimes (Bun, Node.js, Python, Rust, Go, WASM), every function an MCP tool, no per-request cold start. Scope is HTTP/WS Lambdas only — SQS/SNS/S3/ EventBridge-style event sources are out of scope by decision, not omission.
Safety-critical rules (binding)
docs/SAFETY.md — NASA's Power of 10 adapted to Rust —
is binding for all code compiled into the riz binary (src/, i.e.
--lib --bins). Examples (examples/lambdas/*), tests, benches, and fixtures
are exempt by policy.
Working rules that follow from it:
- The enforced lint tier lives in
Cargo.toml[workspace.lints](+clippy.tomlthresholds); only the riz package opts in. scripts/safety-check.sh --gateis a CI gate (prod-only zero-tolerance lints, e.g.clippy::panic).scripts/safety-check.shprints the ratchet report — violation counts may only go down. Never add a site to a ratchet lint; when a lint's count hits zero, promote it (ratchet → gate → enforced) per the protocol in docs/SAFETY.md.- Every
unsafeblock needs#[allow(unsafe_code)]at the site plus a// SAFETY:proof, one operation per block. Any other#[allow]of a safety lint needs an adjacent justification comment. - New code in
src/: nounwrap/expect/panic!/indexing-[]on runtime data, bounded channels only, loops either provably bounded or matching the supervised event-loop contract (docs/SAFETY.md rule 2).
Build & test gates
Run before every push (CI enforces all of them):
cargo fmt --all -- --check
cargo clippy --workspace --all-targets -- -D warnings
./scripts/safety-check.sh --gate
cargo nextest run --workspace -E 'not binary(e2e_smoke_all) and not binary(template_smoke_all) and not binary(perf_regression) and not binary(chaos) and not binary(aws_conformance)'
cargo nextest run --test e2e_smoke_all # isolated: boots the example fleet
cargo nextest run --test template_smoke_all # isolated: scaffolds + boots all six templates
cargo nextest run --test perf_regression --no-capture # isolated: throughput/latency floor + trend
cargo nextest run --test chaos # isolated: deliberate fault injection
cargo nextest run --test aws_conformance # isolated: clones + boots AWS's own Lambda samples (skips offline)
# or the whole flow in one command: scripts/validate.sh
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.
- 2mo ago First seen · 74 lines · 1,086 tokens per session scan A 40f680e482df
riz CLAUDE.md is an instructions file published in the GitHub repository 24X7/riz (3 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 1,086 tokens to every session, about $0.0043 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 2026-08-31.
riz CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| riz CLAUDE.md24X7/riz | Instructions file | 3 | 3mo ago | Apache-2.0 | A | 1,086 | 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 |