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.
npx skills add daffy0208/ai-dev-standards --skill system-diagnosticiangit clone --depth 1 https://github.com/daffy0208/ai-dev-standardsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/daffy0208/ai-dev-standards/system-diagnostician)<a href="https://agentmods.dev/skills/daffy0208/ai-dev-standards/system-diagnostician"><img src="https://agentmods.dev/badge/skills/daffy0208/ai-dev-standards/system-diagnostician/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/daffy0208/ai-dev-standards/system-diagnostician"><img src="https://agentmods.dev/badge/skills/daffy0208/ai-dev-standards/system-diagnostician.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00024 | $0.03311 |
| Opus 5 | $0.00012 | $0.01656 |
| Sonnet 5 | $0.00005 | $0.00662 |
| Haiku 4.5 | $0.00002 | $0.00331 |
Grade A, and why
System Diagnostician 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 8d 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.
How it starts
The opening of the file, as written. The whole thing — 458 lines — stays where its author put it; the contents beside it link to each section on GitHub.
System Diagnostician
Analyze project health and recommend capabilities using Codex-powered system understanding
Purpose
Performs comprehensive project health analysis to diagnose issues, identify missing capabilities, and recommend improvements. Uses Codex to understand project structure, detect anti-patterns, analyze dependencies, and suggest optimal capability additions based on project goals.
When to Use
- New project onboarding: "What does this project need?"
- Health checks: "Is this project following best practices?"
- Gap analysis: "What's missing to achieve X?"
- Performance audits: "Why is this slow?"
- Security audits: "What security risks exist?"
- Dependency audits: "Are dependencies up to date and safe?"
Key Capabilities
- Project Structure Analysis: Understands project type, framework, architecture
- Capability Gap Detection: Identifies missing or incomplete capabilities
- Health Scoring: Quantifies project health across multiple dimensions
- Recommendation Engine: Suggests capabilities with impact/effort estimates
- Dependency Analysis: Checks for outdated, vulnerable, or unnecessary dependencies
- Anti-Pattern Detection: Identifies code smells and architectural issues
- Prioritized Action Plan: Orders recommendations by impact and effort
Inputs
inputs:
project_path: string # Path to project directory
capability_graph: string # Path to capability-graph.json
focus_areas: array # Optional: ["security", "performance", "testing"]
include_metrics: boolean # Include detailed metrics (default: false)
Process
Step 1: Project Discovery
#!/bin/bash
# Analyze project structure
PROJECT_PATH="${1:-.}"
cd "$PROJECT_PATH"
echo "Discovering project structure..."
# Detect project type
PROJECT_TYPE="unknown"
FRAMEWORK="unknown"
if [ -f "package.json" ]; then
PROJECT_TYPE="nodejs"
# Detect framework
if grep -q "\"next\"" package.json; then
FRAMEWORK="nextjs"
elif grep -q "\"react\"" package.json; then
FRAMEWORK="react"
elif grep -q "\"express\"" package.json; then
FRAMEWORK="express"
fi
elif [ -f "requirements.txt" ] || [ -f "pyproject.toml" ]; then
PROJECT_TYPE="python"
fi
# Gather file statistics
FILE_COUNT=$(find . -type f -not -path "./node_modules/*" -not -path "./.git/*" | wc -l)
CODE_FILES=$(find . -name "*.js" -o -name "*.ts" -o -name "*.jsx" -o -name "*.tsx" -o -name "*.py" | wc -l)
TEST_FILES=$(find . -name "*.test.*" -o -name "*.spec.*" | wc -l)
# Check for common directories
HAS_TESTS=$([ -d "tests" ] || [ -d "test" ] || [ -d "__tests__" ] && echo "true" || echo "false")
HAS_DOCS=$([ -f "README.md" ] && echo "true" || echo "false")
HAS_CI=$([ -d ".github/workflows" ] || [ -f ".gitlab-ci.yml" ] && echo "true" || echo "false")
# Package.json analysis
if [ -f "package.json" ]; then
DEPENDENCIES=$(jq -r '.dependencies // {} | keys | length' package.json)
DEV_DEPENDENCIES=$(jq -r '.devDependencies // {} | keys | length' package.json)
SCRIPTS=$(jq -r '.scripts // {} | keys | length' package.json)
fi
# Generate project state
cat > /tmp/project-state.json <<EOF
{
"project_type": "$PROJECT_TYPE",
"framework": "$FRAMEWORK",
"statistics": {
"total_files": $FILE_COUNT,
"code_files": $CODE_FILES,
"test_files": $TEST_FILES
},
"has_tests": $HAS_TESTS,
"has_docs": $HAS_DOCS,
"has_ci": $HAS_CI,
"dependencies": ${DEPENDENCIES:-0},
"dev_dependencies": ${DEV_DEPENDENCIES:-0},
"scripts": ${SCRIPTS:-0}
}
EOF
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 8d ago First seen · 458 lines · 24 tokens per session scan A 06a09eb8b9c9
System Diagnostician is a skill published in the GitHub repository daffy0208/ai-dev-standards (36 stars, last pushed 8mo ago), licensed MIT. It adds 24 tokens to every session and 3,311 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 2026-09-03.
Other skills, from other repositories
analyze-project
Forensic root cause analyzer for Antigravity sessions. Classifies scope deltas, rework patterns, root causes, hotspots, and auto-improves prompts/health.
analyze-project
Forensic root cause analyzer for Claude Code sessions. Classifies scope deltas, rework patterns, root causes, hotspots, and auto-improves prompts/health.
analyze-project
Forensic root cause analyzer for Antigravity sessions. Classifies scope deltas, rework patterns, root causes, hotspots, and auto-improves prompts/health.
analyze-project
Forensic root cause analyzer for Antigravity sessions. Classifies scope deltas, rework patterns, root causes, hotspots, and auto-improves prompts/health.
analyze-project
Forensic root cause analyzer for Antigravity sessions. Classifies scope deltas, rework patterns, root causes, hotspots, and auto-improves prompts/health.
analyze-project
Forensic root cause analyzer for Antigravity sessions. Classifies scope deltas, rework patterns, root causes, hotspots, and auto-improves prompts/health.