Track ManagementSAFE
Multi-harness agentic plugin marketplace for Claude Code, Codex, Cursor, OpenCode, GitHub Copilot, Google Antigravity, and Pi
Overview
Multi-harness agentic plugin marketplace for Claude Code, Codex, Cursor, OpenCode, GitHub Copilot, Google Antigravity, and Pi
adb71e0b2512OBSERVED · 2026-10-02What 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: track-management description: Use this skill when creating, managing, or working with Conductor tracks - the logical work units for features, bugs, and refactors. Applies to spec.md, plan.md, and track lifecycle operations. version: 1.0.0 --- # Track Management Guide for creating, managing, and completing Conductor tracks - the logical work units that organize features, bugs, and refactors through specification, planning, and implementation phases. ## When to Use This Skill - Creating new feature, bug, or refactor tracks - Writing or reviewing spec.md files - Creating or updating plan.md files - Managing track lifecycle from creation to completion - Understanding track status markers and conventions - Working with the tracks.md registry - Interpreting or updating track metadata ## Detailed patterns and worked examples Detailed pattern documentation lives in `references/details.md`. Read that file when the navigation tier above is insufficient. ## Best Practices 1. **One track, one concern**: Keep tracks focused on a single logical change 2. **Small phases**: Break work into phases of 3-5 tasks maximum 3. **Verification after phases**: Always include verification tasks 4. **Update markers immediately**: Mark task status as you work 5. **Record SHAs**: Always note commit SHAs for completed tasks 6. **Review specs before planning**: Ensure spec is complete before creating plan 7. **Link dependencies**: Explicitly note track dependencies 8. **Archive, don't delete**: Preserve completed tracks for reference 9. **Size appropriately**: Keep tracks between 1-5 days of work 10. **Clear acceptance criteria**: Every requirement must be testable
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| 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 (1)
CLAUDE.md
Gates applied: no_behavioural_pass.
adb71e0b2512full audit observations/trust-audit/skill/wshobson__track-management.json · Report an issue / request a re-scanAudit history
Every audit this skill has had.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-02 | adb71e0b2512 | SAFE | B | 89 | first audit |
Questions
What does the Track Management skill do?
Multi-harness agentic plugin marketplace for Claude Code, Codex, Cursor, OpenCode, GitHub Copilot, Google Antigravity, and Pi
Is Track Management safe to install?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean skill reads B.
What can Track Management 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 (adb71e0b2512), read on 2026-10-02. The repository is watched, and a new audit runs when it changes — this is the first audit.