diagnose

A guide for systematically checking the health of an AI workflow across prompts, context use, tools, and other quality areas.

In plain words
What is it for?
Use it to audit prompts, context management, tool design, error handling, and overall workflow quality.
Why use it?
It turns vague concerns about an agent into specific findings and scores that show where the workflow needs attention.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/sharpdeveye/maestro/diagnose
Any agent
npx skills add sharpdeveye/maestro --skill diagnose
Clone the repo
git clone --depth 1 https://github.com/sharpdeveye/maestro

Made for: Claude Code, Codex.

Per session 27 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,359 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00027 $0.01359
Opus 5 $0.00014 $0.00679
Sonnet 5 $0.00005 $0.00272
Haiku 4.5 $0.00003 $0.00136

Measured 3d ago against content hash 0c7859636631, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

diagnose scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

source/skills/diagnose/SKILL.md · 141 lines

How it starts

The opening of the file, as written. The whole thing — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MANDATORY PREPARATION

Invoke /agent-workflow — it contains workflow principles, anti-patterns, and the Context Gathering Protocol. Follow the protocol before proceeding — if no workflow context exists yet, you MUST run /teach-maestro first.


Perform a systematic diagnostic scan across 5 dimensions. For each dimension, score 1-5 and provide specific findings.

Dimension 1: Prompt Quality (1-5)

Evaluate:

  • Structure (4-zone pattern: role, context, instructions, output)
  • Output schema definition (explicit vs. implicit)
  • Instruction clarity (specific vs. vague)
  • Edge case handling (addressed vs. ignored)
  • Anti-patterns present (wall of text, contradictions, implicit format)

Dimension 2: Context Efficiency (1-5)

Evaluate:

  • Context budget allocation (planned vs. ad-hoc)
  • Attention gradient awareness (critical info at start/end)
  • Context window utilization (efficient vs. wasteful)
  • State management (explicit vs. implicit)
  • Memory strategy (appropriate for conversation length)

Dimension 3: Tool Health (1-5)

Evaluate:

  • Tool count (3-7 ideal, 13+ problematic)
  • Description quality (specific vs. vague)
  • Error handling (graceful vs. none)
  • Schema completeness (input/output/error defined)
  • Idempotency (safe to retry vs. side-effect prone)
  • Scope attribution: Distinguish between project-configured tools (e.g., custom scripts, project MCP servers) and agent-level tools (e.g., built-in IDE tools, global MCP servers). Only flag tool overhead for tools the project can actually control

Dimension 4: Architecture Fitness (1-5)

Evaluate:

  • Topology appropriateness (single vs. multi-agent justified)
  • Agent boundaries (clear vs. overlapping)
  • Handoff protocols (structured vs. ad-hoc)
  • Observability (decisions logged vs. black box)
  • Cost awareness (budgeted vs. unbounded)

Dimension 5: Safety & Reliability (1-5)

Evaluate:

  • Input validation (present vs. absent)
  • Output filtering (PII, content policy) — scope contextually: data flowing between a user's own frontend and backend (e.g., authenticated sessions, internal APIs) is lower risk than data exposed to external services or third-party APIs
  • Cost controls (ceilings set vs. unbounded)
  • Error recovery (fallbacks vs. crash)
  • Evaluation strategy (golden tests vs. "it seems to work")

Read the full file on GitHub · 141 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 3d ago First seen · 141 lines · 27 tokens per session scan A 0c7859636631

Subscribe to this mod's changes

diagnose is a skill published in the GitHub repository sharpdeveye/maestro (415 stars, last pushed 4mo ago), licensed MIT. It adds 27 tokens to every session and 1,359 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

agent-self-scheduling

Schedule AI agent runs with cron, loops, or external clocks while avoiding unsafe tight autonomous timers.

sickn33/agentic-awesome-skills · 24 tokens

skill-creator

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

agnt-gg/agnt · 64 tokens

agnt-plugin-builder

End-to-end workflow for creating, building, installing, and hot-reloading AGNT plugins entirely from chat. Use this skill whenever the user asks to 'build a plugin', 'create an AGNT plugin', 'add a new tool to AGNT', 'integrate X with AGNT' (where X is an API or service), 'make a plugin for [service]', or wants to…

agnt-gg/agnt · 201 tokens

annie-universal-api-orchestrator

Use AGNT's stored OAuth tokens and API keys to call ANY third-party API directly from the orchestrator, without building a tool or plugin first. Use this skill whenever the user asks you to "do something with my GitHub / Gmail / Drive / Slack / Notion / Stripe / Shopify / Discord / Linear / Jira / Vercel / Netlify /…

agnt-gg/agnt · 208 tokens

hermes-subagent

Delegate complex, autonomous, or tool-heavy tasks to a Hermes Agent sub-agent running in the AGNT sandbox. Hermes is Nous Research's self-improving Python agent (47 built-in tools, persistent memory, skills system, sub-agent delegation). Use this skill whenever the user asks Annie to "delegate to Hermes", "have Hermes…

agnt-gg/agnt · 218 tokens

mcp-builder

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

agnt-gg/agnt · 61 tokens