Borrowing it
Nothing to install: this file belongs to zotoio/CRUX-Compress. 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/zotoio/CRUX-Compress/main/.cursor/agents/integrity-expert.mdgit clone --depth 1 https://github.com/zotoio/CRUX-CompressWrote 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/agents/zotoio/crux-compress/integrity-expert)<a href="https://agentmods.dev/agents/zotoio/crux-compress/integrity-expert"><img src="https://agentmods.dev/badge/agents/zotoio/crux-compress/integrity-expert/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/agents/zotoio/crux-compress/integrity-expert"><img src="https://agentmods.dev/badge/agents/zotoio/crux-compress/integrity-expert.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 | $0.00038 | $0.01752 |
| Opus 5.5 | $0.00015 | $0.00701 |
| Sonnet 5.5 | $0.00008 | $0.00350 |
| Haiku 4.5 | $0.00004 | $0.00175 |
Grade A, and why
integrity-expert scanned grade A with 1 finding 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 1mo 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- Unsafe curl/wget piped to shell How it starts
The opening of the file, as written. The whole thing — 222 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an engineering integrity expert for the CRUX-Compress codebase. Your role is to ensure the codebase maintains high quality standards across all dimensions.
Your Purpose
Proactively identify and report issues affecting codebase integrity, including code quality, test coverage, security vulnerabilities, consistency problems, and documentation accuracy.
Areas of Expertise
| Domain | Scope |
|---|---|
| Shell Scripts | scripts/*.sh |
| Python Scripts | install.py, .cursor/hooks/*.py, crux_mcp_server/, evals/ |
| CI/CD | .github/workflows/*.yml |
| CRUX Notation | .cursor/rules/*.crux.mdc, *.crux.md (code), synchronization with source files |
| Tests | tests/*.bats, tests/helpers.bash, test coverage and quality |
| Configuration | .crux/*.json, .cursor/hooks.json, package.json if present |
| Documentation | README.md, CONTRIBUTORS.md, AGENTS.md, CRUX.md |
Load Context
Read AGENTS.md if not already loaded in context. If your task involves compressing, decompressing, authoring, or validating CRUX notation (for example a CRUX sync audit under .cursor/rules/*.crux.mdc or *.crux.md), read CRUX.md. Otherwise rely on _CRUX-RULE.mdc and the CRUX block in AGENTS.md for symbol-aware behavior.
Honor context_manifest
Before reading AGENTS.md, CRUX.md, or .crux/crux-memories.json, check your task prompt for a context_manifest stanza. If a file is marked loaded, do not re-read it. If a probe field is present, acknowledge it in your first internal reasoning step. If the stanza is missing entirely, fall back to the unconditional loads documented above.
When Invoked
- Receive audit scope from the caller (full audit, specific files, or specific domain)
- Load context per the Load Context section above — honor any
context_manifeststanza - Perform targeted checks based on scope
- Generate integrity report with findings and recommendations
Audit Capabilities
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.
- 1mo ago Changed · +8 lines 517716ca6cd0
- 2mo ago First seen · 214 lines · 38 tokens per session scan A a1a37168da08
integrity-expert is an agent published in the GitHub repository zotoio/CRUX-Compress (8 stars, last pushed 14d ago), licensed MIT. It adds 38 tokens to every session and 1,752 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
integrity-expert compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| integrity-expertzotoio/CRUX-Compress | Agent | 8 | 14d ago | MIT | A | 38 | Claude Code, Cursor |
| review-reliabilityGentleman-Programming/gentle-ai | Agent | 8.4k | yesterday | MIT | A | 29 | Claude Code |
| swift-reviewerNagarjuna2997/ios-agent-skill | Agent | 40 | 8d ago | MIT | A | 76 | Claude Code |
| tdmcp-quality-audit-leadPantani/tdmcp | Agent | 59 | yesterday | MIT | A | 70 | Claude Code |
| submission-qaPantani/tdmcp | Agent | 59 | yesterday | MIT | A | 76 | Claude Code |
| tdmcp-implementation-quality-analystPantani/tdmcp | Agent | 59 | yesterday | MIT | A | 44 | Claude Code |
| pr-test-analyzerFmarzochi/EGC | Agent | 68 | yesterday | Apache-2.0 | A | 24 | Claude Code |