Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

Back to skills

Diagnose Loop Health

ASecurity

Use when a configured loop misbehaves, produces unexpected results, or its setup soundness is questioned. Not for tasks that require source or remote-system changes, not for loop design.

35 stars
0 votes
0 copies
1 views
Added 9/12/2026
ai-agents

Security Analysis

A100/100

Scanned 9/12/2026

Install to Claude Code

$npx -y skills add OutlineDriven/odin-claude-plugin --skill diagnose-loop-health --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Diagnose Loop Health?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Diagnose Loop Health
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/outlinedriven-diagnose-loop-health-odin-claude-plugin/badge)](https://www.skillsdirectory.com/skills/outlinedriven-diagnose-loop-health-odin-claude-plugin)

More formats (shields.io, HTML) on the badges page.

Download Zip
Files
SKILL.md
---
name: diagnose-loop-health
description: 'Use when a configured loop misbehaves, produces unexpected results, or its setup soundness is questioned. Not for tasks that require source or remote-system changes, not for loop design.'
---

# Diagnose loop health

## Contract

| Field | Bound contract |
|---|---|
| Trigger | A configured loop misbehaves, or the user asks whether the loop setup is sound |
| Authority | Read-only. No file, VCS, credential, paid, published, deployed, or remote mutation. |
| Side effect | A severity report with at most three prioritized actions and a nonzero exit on blocked; no file mutation |
| Done | Severity is healthy, warning, or blocked with exit 0, 1, or 2, and each finding names the exact missing or stale charter, state, gate, or budget file |

## Inputs

The user must supply the loop directory to inspect. No file is created or written. The skill reads four file classes from that directory: the charter file, the state file, the gate file, and the budget file. If the directory is not named, ask for it and stop until it is supplied.

## Procedure

1. Obtain the loop directory from the user. If absent, stop and ask; do not infer or create one. **Done when:** the loop directory is supplied or the skill stops to ask.

2. Bound scope to read-only inspection of that directory. Do not write, create, rename, delete, or move any file. **Done when:** scope is bounded to read-only inspection.

3. Locate and read the loop's charter file, state file, gate file, and budget file. For each, record presence and freshness: missing if absent; stale if its content does not match the loop's declared cadence, gate thresholds, or budget limits. **Done when:** all four files are read with presence and freshness recorded.

4. Classify severity on the ladder: healthy if all four files are present and current; warning if any file is missing or stale but the loop can still run; blocked if a required charter or state file is absent or unreadable. **Done when:** severity is classified healthy, warning, or blocked.

5. For warning or blocked, emit at most three prioritized actions ordered by impact, each naming the exact missing or stale file by path and class. **Done when:** zero to three prioritized actions are emitted, each naming the file by path and class.

6. Exit 0 for healthy, 1 for warning, 2 for blocked. **Done when:** the exit code matches the severity.

## Failure and recovery
- Missing loop directory: report blocked naming the absent directory, exit 2; do not create it.
- Unreadable file (permission denied or parse error): report blocked naming the file and the error, exit 2; do not mutate or skip it silently.
- Ambiguous severity where both warning and blocked conditions hold: classify as the higher severity, blocked, and exit 2.
- Partial result is forbidden: if any required file cannot be read, escalate to blocked rather than emit a warning or healthy verdict.
- Never swallow an error or assert the done predicate when a file is unreadable.

## Output
A severity report carrying one of healthy, warning, or blocked, the matching exit code 0, 1, or 2, and zero to three prioritized actions, each naming the exact missing or stale charter, state, gate, or budget file by path and class, ordered obtain-dir → bound-scope → read-files → classify → emit-actions → exit.

Attribution

OutlineDrivenOutlineDriven
View sourceMore from OutlineDriven →
SSkills DirectorySkills Directory

Know which skills are safe — weekly.

Best new skills + every skill we flagged as malicious. From the team that scanned 103,619.

Join free

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 (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Know which skills are safe — weekly.

Best new skills + every skill we flagged as malicious. From the team that scanned 103,619.

Join free

Related Skills

Caveman

Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.

1023331 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

686011 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

651 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →