EstimateCAUTION
Overview
An agent skill published by paperclipai.
144776592aa6OBSERVED · 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: estimate
description: Effort breakdown and estimation
metadata:
sources:
- kind: github-file
repo: Donchitos/Claude-Code-Game-Studios
path: .claude/skills/estimate/SKILL.md
commit: 7d08e396e354a3601b706109b072f4573fe0007b
attribution: Donchitos
license: MIT
usage: referenced
---
Effort breakdown and estimation.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 (2)
.agents/skills/company-creator
.claude/skills/company-creator
Gates applied: no_behavioural_pass.
144776592aa6full audit observations/trust-audit/skill/paperclipai__estimate.json · Report an issue / request a re-scanAudit history
Every audit this skill has had.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-13 | 144776592aa6 | CAUTION | B | 89 | first audit |
Questions
Is Estimate safe to install?
With care. The audit graded it B (89/100) and found 2 things worth knowing before you trust this skill, listed below with the exact line each was found on.
What can Estimate 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 (144776592aa6), read on 2026-10-13. The repository is watched, and a new audit runs when it changes — this is the first audit.