Runs

Name: Runs
Author: briandconnelly

ASecurity

Date: 2026-07-11 Run: treatment with the skill. | # | Assertion | Result | Evidence | | --- | --- | --- | --- | | 1 | Report a clean outcome | PASS | The output says “Clean — no findings.” | | 2 | Avoid manufactured findings | PASS | All rule and severity counts are zero. | | 3 | Accept the explicit default and override | PASS | The assessment recognizes the stated precedence. | | 4 | Avoid an R5 finding | PASS | R5 has zero findings. | Total: 4/4.

3 stars
0 votes
0 copies
2 views
Added September 3, 2026

ai-agents

Security analysis

A100/100

Pro scans all 20 files and shows the line behind each finding

Scanned September 3, 2026

npx -y skills add briandconnelly/codex-in-claude --skill runs --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Runs?

Add the live security badge to your README. It updates with every re-scan.

[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/briandconnelly-runs-be117ad7/badge)](https://www.skillsdirectory.com/skills/briandconnelly-runs-be117ad7)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro

SKILL.md

# Scenario 5 — With-Skill Scoring

Date: 2026-07-11
Run: treatment with the skill.

| # | Assertion | Result | Evidence |
| --- | --- | --- | --- |
| 1 | Report a clean outcome | PASS | The output says “Clean — no findings.” |
| 2 | Avoid manufactured findings | PASS | All rule and severity counts are zero. |
| 3 | Accept the explicit default and override | PASS | The assessment recognizes the stated precedence. |
| 4 | Avoid an R5 finding | PASS | R5 has zero findings. |

Total: 4/4.

## Scored Output

## Summary

- R1 Distinguishability: 0 findings
- R2 Explicit strength: 0 findings
- R3 Verifiability: 0 findings
- R4 Atomic obligations: 0 findings
- R5 Reachable precedence: 0 findings
- Material: 0 findings
- Minor: 0 findings

Clean — no findings.
The document clearly separates informative background under **Context** from binding instructions under **Rules**, makes each obligation checkable and explicit in strength, and states the reachable precedence between rules 6 and 7.