Skip to content
Back to skills

Agents Md Retrospective

ASecurity

Updates AGENTS.md after a repeated verified failure. Do not use for one-off preferences or speculative rules.

  • 2 stars
  • 0 votes
  • 0 copies
  • 0 views
  • Added November 7, 2026
ai-agents

Security analysis

A100/100

Pro scans all 2 files and shows the line behind each finding

Scanned November 7, 2026

npx -y skills add Mesteriis/Engineering-Bible-AI --skill agents-md-retrospective --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Agents Md Retrospective?

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

Security grade badge for Agents Md Retrospective
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/mesteriis-agents-md-retrospective/badge)](https://www.skillsdirectory.com/skills/mesteriis-agents-md-retrospective)

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
---
name: agents-md-retrospective
description: "Updates AGENTS.md after a repeated verified failure. Do not use for one-off preferences or speculative rules."
---

# AGENTS.md Retrospective

Make instruction updates only when the pattern is durable.

## Workflow

1. Read the relevant local and global instruction files.
2. Identify the exact repeated failure or missing rule.
3. Add the smallest durable instruction that would have prevented it.
4. Avoid duplicating existing rules.
5. Validate by grepping the final instruction and checking for conflicts.

## Rules

- Do not add secrets or environment-specific sensitive values.
- Do not turn AGENTS.md into a skill body.
- Prefer routing rules and validation commands over broad role prose.
- Respect scoped directory instructions.

## Output

- changed instruction file
- rule added or changed
- why it belongs there
- validation command

Files in this skill

  • SKILL.md893 B
  • agents/openai.yaml190 B

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.