InvestigateCAUTION
The Claude Code background agent for Linear, Slack, Github, GitLab etc. you deploy anywhere. Supports Codex, Cursor, Gemini, and Opencode harnesses too.
Overview
The Claude Code background agent for Linear, Slack, Github, GitLab etc. you deploy anywhere. Supports Codex, Cursor, Gemini, and Opencode harnesses too.
a792ab0e17bbOBSERVED · 2026-10-13What it tells the agent
The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.
--- name: investigate description: Research the codebase to answer questions. Search for relevant files, gather context, and provide clear answers. --- # Investigate Research the codebase and provide a clear, direct answer to the question. ## Approach 1. **Search** — Search the codebase for relevant files, functions, and patterns 2. **Read** — Read necessary files to understand the implementation 3. **Gather context** — Use tools as needed to collect comprehensive information 4. **Answer** — Provide a clear, direct answer using your findings ## Answer Format - Present in Linear-compatible markdown - Use `+++Section Name\n...\n+++` for collapsible sections with detailed information - Include code references with file paths and line numbers - For @mentions, use the Linear profile URL format from `<assignee>` context (e.g. `https://linear.app/<workspace>/profiles/<username>`) - Be complete but concise — answer the question directly without unnecessary preamble
Trust audit
CAUTIONgrade B · trust 89/100 Install with care. The audit found things worth knowing before you trust its output.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | WARN |
| L1 | Static analysis of the code | NA |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (5)
.claude/skills/cyrus-setup
.claude/skills/cyrus-setup-claude-auth
.claude/skills/cyrus-setup-endpoint
.claude/skills/cyrus-setup-github
.claude/skills/cyrus-setup-gitlab
Gates applied: no_behavioural_pass.
a792ab0e17bbfull audit observations/trust-audit/skill/cyrusagents__investigate.json · Report an issue / request a re-scanAudit history
Every audit this skill has had.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-13 | a792ab0e17bb | CAUTION | B | 89 | first audit |
Questions
What does the Investigate skill do?
The Claude Code background agent for Linear, Slack, Github, GitLab etc. you deploy anywhere. Supports Codex, Cursor, Gemini, and Opencode harnesses too.
Is Investigate safe to install?
With care. The audit graded it B (89/100) and found 5 things worth knowing before you trust this skill, listed below with the exact line each was found on.
What can Investigate access on my machine?
The audit observed no filesystem, network or shell use at all in its source.
How current is this page?
The grade is for one exact copy of the source (a792ab0e17bb), read on 2026-10-13. The repository is watched, and a new audit runs when it changes — this is the first audit.