Borrowing it
Nothing to install: this file belongs to Acquiredl/Acu. 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/Acquiredl/Acu/master/CLAUDE.mdgit clone --depth 1 https://github.com/Acquiredl/AcuWrote 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/acquiredl/acu/claude-md)<a href="https://agentmods.dev/instructions/acquiredl/acu/claude-md"><img src="https://agentmods.dev/badge/instructions/acquiredl/acu/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/acquiredl/acu/claude-md"><img src="https://agentmods.dev/badge/instructions/acquiredl/acu/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 | $0.01228 | $0.01228 |
| Opus 5.5 | $0.00491 | $0.00491 |
| Sonnet 5.5 | $0.00246 | $0.00246 |
| Haiku 4.5 | $0.00123 | $0.00123 |
Grade A, and why
Acu 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Acu
A framework for building LLM-driven pipelines where the filesystem defines the program. You create directories for stages, CLAUDE.md files for behavior, and quality gates for reliability. The LLM reads this structure and executes it — templates let you replicate the pattern across new domains.
Because LLMs are probabilistic, Acu treats quality gates as a first-class concern: every stage transition must pass a deterministic check before work advances. This is what makes the output reliable despite the executor being non-deterministic.
Anchor Metaphor
Acu is an office. Each pipeline is a department with its own charter (its CLAUDE.md). Each stage is a desk inside the department. Between desks there is an inspection point — a quality gate — that signs off on work before it advances. A work unit is a project moving from desk to desk through the department. The department's final deliverable is the project's report.
The Orchestrator is Operations — the only role with cross-department visibility. It routes work, reviews outputs against standards, and surfaces framework-level improvements back into how departments run. Departments stay isolated from each other; Operations is the one seam.
This is the mental model. The rest of this document — the mechanical names (pipeline, stage, gate, unit, deliverable, Orchestrator) and the structural rules — are how the office runs in practice.
Architectural Principles
Acu's architecture is organized around isolation, gates, and structure:
- Isolation — Each pipeline runs independently with its own stages, gates, and context. No pipeline can reach into another. The Orchestrator is the only component with cross-pipeline visibility.
- Two-layer gates — Every stage transition passes a deterministic structural check (file existence, word counts, section headers, cross-references) followed, where configured, by an LLM-based semantic evaluation across three tiers (stage, pipeline, system). The structural layer is binary; the semantic layer implements the Evaluator-Optimizer loop with bounded retries. Nothing advances without passing both.
- Structure as schema — Templates enforce directory layout and file requirements. CLAUDE.md files scope what context gets loaded. Validation is structural, not semantic.
- Audit trail — Every transition is logged with session ID and SHA256.
syslog.shaggregates across pipelines. - Threat model — Pipeline isolation, input validation, and defined attack surfaces. See
THREAT-MODEL.md.
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 · 70 lines · 1,228 tokens per session scan A b21b11ae05b6
Acu CLAUDE.md is an instructions file published in the GitHub repository Acquiredl/Acu (2 stars, last pushed 2mo ago), licensed MIT. It adds 1,228 tokens to every session, about $0.0049 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.
Acu CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| Acu CLAUDE.mdAcquiredl/Acu | Instructions file | 2 | 2mo ago | MIT | A | 1,228 | 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 |