Skip to content
Agentmart
Submit a tool

mini-a-runtime-diagnostics

Diagnose Mini-A skipped tools, failed goals, and unexpected answers using effective configuration, transcripts, and runtime evidence.

Skill by OpenAF

IndexedApache-2.0★ 1
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/openaf-mini-a-runtime-diagnostics

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Diagnose Mini-A skipped tools, failed goals, and unexpected answers using effective configuration, transcripts, and runtime evidence.

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/mini-a-runtime-diagnostics

What's inside

Skill name
mini-a-runtime-diagnostics
Description
Diagnose Mini-A skipped tools, failed goals, and unexpected answers using effective configuration, transcripts, and runtime evidence.
License
Apache-2.0
Instructions
12 lines in SKILL.md · view on GitHub

Files (2)

  • SKILL.md
  • diagnostics.md · references/

SKILL.md (first lines)

# Diagnose the running Mini-A agent

Use for skipped tools, failed goals, unexpected answers, or uncertainty about whether selected skills were followed. Requires access to relevant configuration and logs; collect only necessary evidence and redact credentials.

1. Record the entry point, invocation, working directory, installed package or checkout path, and symptom. Inspect effective options and environment model routing without printing keys. Consult @references/diagnostics.md for the boundaries that commonly explain surprises.
2. Trace the relevant lifecycle: goal and configuration, available tool schemas, skill discovery/selection/loading, actual tool requests, returned errors/results, and final output. Separate confirmed causes from hypotheses. Tool availability, skill activation, and successful loading do not prove execution or compliance.
3. Compare the source under inspection with the runtime actually launched. An installed oPack can differ from a checkout; a long-lived web server can still run older code. Verify paths and running process configuration before attributing behavior to an edit.
4. Reproduce with a small representative goal and `debug=true` when appropriate. Preserve existing state and avoid exposing sensitive prompt or log content. If a prerequisite is unavailable, report the precise boundary instead of inventing execution evidence.
5. Make corrective changes within the user's authorized scope. Treat configuration edits, rebuilding/repackaging, and restarting processes as separate actions; choose only the steps needed by the observed cause. Verify afterward against the same entry point and runtime that exhibited the problem.

Completion: report the cause and evidence, correction performed, reproduction/verification results, and remaining uncertainty. For skill adherence, inspect tool-call or output-artifact evidence beyond activation metrics.

From OpenAF/mini-a, Apache-2.0.

More from OpenAF/mini-a

Signals

Stars
1
Forks
0
Open issues
0
Last commit (this folder)
Oct 24, 2026 (6 days ago)
Last release
Oct 14, 2026 (16 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License
Apache-2.0
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from OpenAF

Cite this page

mini-a-runtime-diagnostics skill. Agent Mart. https://agentmart.dev/skills/openaf-mini-a-runtime-diagnostics (last updated 2026-10-24)