Borrowing it
Nothing to install: this file belongs to Renn-Labs/Looptimal. 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/Renn-Labs/Looptimal/main/CLAUDE.mdgit clone --depth 1 https://github.com/Renn-Labs/LooptimalWrote 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/renn-labs/looptimal/claude-md)<a href="https://agentmods.dev/instructions/renn-labs/looptimal/claude-md"><img src="https://agentmods.dev/badge/instructions/renn-labs/looptimal/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 5.1 | $0.00449 | $0.00449 |
| Opus 5 | $0.00225 | $0.00225 |
| Sonnet 5 | $0.00090 | $0.00090 |
| Haiku 4.5 | $0.00045 | $0.00045 |
Grade A, and why
Looptimal 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 6d 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.
What it actually says
Looptimal — repo guidance for AI agents
Looptimal turns an objective into a delivered, verified outcome: a sealed acceptance suite, the
right loop, a war-game pass, domain-expert execution (maker ≠ checker), and a separate verifier.
Keep the core generic, dependency-light, and honest about its gates (see CONTRIBUTING.md,
SECURITY.md, RELEASE.md).
Build Journal — capture the concepts, not the changelog
Append an entry to .buildlog/journal.md (create it, and add .buildlog/ to .gitignore, if this
is the first) only when there's a high-level idea with real weight:
- a principle the build taught (or re-taught) you,
- a decision with lasting consequence, and why,
- a limitation you're choosing to own rather than hide,
- a gotcha that revealed something deeper than its immediate fix,
- a genuine milestone.
Skip routine progress, mechanical fixes, and anything you'd only care about this week. Frequency follows insight, not activity — a stretch with nothing worth logging is fine.
Format per entry:
## <ISO timestamp> — <category> — <short title>
<commit: optional SHA if directly tied to a change>
1-3 sentences, first person, honest. The concept and why it matters — not the play-by-play.
No marketing voice: explain it to a teammate, don't pitch it.
Category is one of: breakthrough | learning | gotcha | decision | milestone | honest-limitation
Rules:
- Be honest about what didn't work. Owned limitations and honest misses make better build-in-public content than polished wins — don't sand them off.
- Don't self-edit into marketing copy. This is raw material; a separate process shapes it later.
- Never put secrets, credentials, internal paths, or proprietary details in an entry — this file is read by that separate process.
.buildlog/is gitignored on purpose: raw internal narrative must never ship in the public OSS history.
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.
- 6d ago First seen · 41 lines · 449 tokens per session scan A c223c411f5c4
Looptimal CLAUDE.md is an instructions file published in the GitHub repository Renn-Labs/Looptimal (4 stars, last pushed 1mo ago), licensed MIT. It adds 449 tokens to every session, about $0.0022 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 2026-08-31.
Other instructions, from other repositories
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).
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).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
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.