Date: 2026-07-11 Run: treatment with the skill. | # | Assertion | Result | Evidence | | --- | --- | --- | --- | | 1 | One consolidated R2/R3 finding | PASS | Finding 1 uses R2 as primary and R3 as secondary. | | 2 | Explain ambiguous strength and unverifiability | PASS | Finding 1 identifies both “Generally try” and the absence of observable safeguards. | | 3 | Preserve policy as an author decision | PASS | Both alternatives retain an author-defined placeholder instead of inventing policy. | ...
Scanned 9/3/2026
Install to Claude Code
npx -y skills add briandconnelly/codex-in-claude --skill runs --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Runs?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/briandconnelly-runs-ce60bea1)More formats (shields.io, HTML) on the badges page.
# Scenario 6 — With-Skill Scoring
Date: 2026-07-11
Run: treatment with the skill.
| # | Assertion | Result | Evidence |
| --- | --- | --- | --- |
| 1 | One consolidated R2/R3 finding | PASS | Finding 1 uses R2 as primary and R3 as secondary. |
| 2 | Explain ambiguous strength and unverifiability | PASS | Finding 1 identifies both “Generally try” and the absence of observable safeguards. |
| 3 | Preserve policy as an author decision | PASS | Both alternatives retain an author-defined placeholder instead of inventing policy. |
| 4 | Separate minor R1 finding for history | PASS | Finding 2 moves the unchanged statement to Context and marks it minor. |
| 5 | Report one material and one minor finding | PASS | The summary reports material 1 and minor 1 without double-counting. |
Total: 5/5.
## Scored Output
## Findings
### 1. Ambiguous and unverifiable deletion guidance
- **Rule ID:** R2; also R3
- **Location:** `Rules`, first list item
- **Quoted text:** “Generally try to be careful when deleting customer records.”
- **Why it fails:** “Generally try to” does not establish whether the guidance is mandatory, a defeasible default, or nonbinding context.
“Be careful” also identifies no observable safeguard, so compliance cannot be verified.
- **Severity:** Material
- **Suggested rewrite:** Author decision required.
First define the observable safeguard intended by “careful,” then choose one of these semantic alternatives:
- **Mandatory:** “Before deleting customer records, you must `<author-specified observable safeguard>`.”
- **Default:** “Prefer `<author-specified observable safeguard>` before deleting customer records unless `<author-specified override condition>`.”
- **Nonbinding context:** Move outside `Rules`: “Deleting customer records warrants particular care.”
### 2. Historical context placed in the rules section
- **Rule ID:** R1
- **Location:** `Rules`, second list item
- **Quoted text:** “The retention service was introduced during the 2024 storage migration.”
- **Why it fails:** This is discretionary historical context rather than a behavioral constraint, so it does not belong in the rules section.
- **Severity:** Minor
- **Suggested rewrite:** Move it unchanged to a context section:
```markdown
## Context
The retention service was introduced during the 2024 storage migration.
```
## Summary
- **By rule:** R1: 1; R2: 1; R3: 1; R4: 0; R5: 0.
- **By severity:** Material: 1; Minor: 1.
The document mixes one ambiguously binding, unverifiable instruction with one historical fact under `Rules`.
The deletion policy needs an author-defined, observable safeguard and explicit strength, while the migration history should be separated into context.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!