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 agentmods add skills/neverinfamous/mysql-mcp/agent-observability-eval-bootstrapnpx skills add neverinfamous/mysql-mcp --skill agent-observability-eval-bootstrapgit clone --depth 1 https://github.com/neverinfamous/mysql-mcpWrote 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/neverinfamous/mysql-mcp/agent-observability-eval-bootstrap)<a href="https://agentmods.dev/skills/neverinfamous/mysql-mcp/agent-observability-eval-bootstrap"><img src="https://agentmods.dev/badge/skills/neverinfamous/mysql-mcp/agent-observability-eval-bootstrap.svg" alt="Measured on agentmods" 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 | $0.00135 | $0.24026 |
| Opus 5 | $0.00068 | $0.12013 |
| Sonnet 5 | $0.00027 | $0.04805 |
| Haiku 4.5 | $0.00014 | $0.02403 |
Grade A, and why
agent-observability-eval-bootstrap 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 5d 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.
This is a copy
97% identical to agent-observability-eval-bootstrap — 4 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 1,368 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Backend
Detection — At the start of every invocation, before taking any action, determine which backend to use:
- If the user passed
--backend pupanywhere in their invocation → use pup mode immediately, regardless of whether MCP tools are present. Skip steps 2–4. - Check whether MCP tools are present in your active tool list. The canonical signal is whether
mcp__datadog-llmo-mcp__list_llmobs_evalsappears in your available tools. - If MCP tools are present → use MCP mode throughout. Call MCP tools exactly as named in this skill's workflow sections.
- If MCP tools are absent → check whether
pupis executable: runpup --versionvia Bash. A JSON response containing"version"confirms pup is available. - If pup responds → use pup mode throughout. Translate every MCP tool call to its pup equivalent using the Tool Reference appendix at the bottom of this file.
- If neither is available → stop and tell the user:
"Neither the Datadog MCP server nor the pup CLI is available. Connect the MCP server (
claude mcp add --scope user --transport http datadog-llmo-mcp 'https://mcp.datadoghq.com/api/unstable/mcp-server/mcp?toolsets=llmobs') or install pup."
--backend pup is accepted anywhere in the invocation arguments and is stripped before passing remaining args to the skill logic.
pup invocation rules:
- Invoke via Bash:
pup llm-obs <subcommand> [flags] - pup always outputs JSON. Parse directly — no content-block unwrapping (unlike MCP results, which may wrap JSON in
[{"type": "text", "text": "<json>"}]). - If pup returns an auth error, tell the user to run
pup auth loginand stop. - Parallelization: issue multiple Bash tool calls in a single message (one pup command per call).
- Time flags: pup accepts bare duration strings (
1h,7d,30m) and RFC3339 timestamps. Do not usenow--prefixed strings — strip the prefix when converting from a skill--timeframeargument:now-7d→7d,now-24h→24h,now-30d→30d. --summaryonpup llm-obs spans searchstrips payload fields to essential metadata only. Use it in bulk/search phases where content is not needed.
Invocation ID: At the very start of each invocation, before any MCP tool call, generate an 8-character hex invocation ID (e.g., 3a9f1c2b). Keep it constant for the entire invocation.
Intent tagging: On every MCP tool call, prefix telemetry.intent with skill:agent-observability-eval-bootstrap[<inv_id>] — followed by a description of why the tool is being called. On the first MCP tool call only, use skill:agent-observability-eval-bootstrap:start[<inv_id>] — instead (note the :start suffix). Example first call: skill:agent-observability-eval-bootstrap:start[3a9f1c2b] — Phase 0: map existing eval coverage for task-cruncher
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.
- 5d ago First seen · 1,368 lines · 135 tokens per session scan A a80db3d6c2e5
agent-observability-eval-bootstrap is a skill published in the GitHub repository neverinfamous/mysql-mcp (10 stars, last pushed 5d ago), licensed MIT. It adds 135 tokens to every session and 24,026 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 0 findings. It is 97% identical to agent-observability-eval-bootstrap, differing in 4 lines, and is treated as a copy.
Other skills, from other repositories
laravel-actions
Build, refactor, and troubleshoot Laravel Actions using lorisleiva/laravel-actions. Use when implementing reusable action classes (object/controller/job/listener/command), converting service classes/controllers/jobs into actions, orchestrating workflows via faked actions, or debugging action entrypoints and wiring.
livewire-development
Use for any task or question involving Livewire. Activate if user mentions Livewire, wire: directives, or Livewire-specific concepts like wire:model, wire:click, invoke this skill. Covers building new components, debugging reactivity issues, real-time form validation, loading states, migrating from Livewire 2 to 3…
mcp-development
Use this skill for Laravel MCP development only. Trigger when creating or editing MCP tools, resources, prompts, or servers in Laravel projects. Covers: artisan make:mcp- generators, mcp:inspector, routes/ai.php, Tool/Resource/Prompt classes, schema validation, shouldRegister(), OAuth setup, URI templates, read-only…
laravel-best-practices
Apply this skill whenever writing, reviewing, or refactoring Laravel PHP code. This includes creating or modifying controllers, models, migrations, form requests, policies, jobs, scheduled commands, service classes, and Eloquent queries. Triggers for N+1 and query performance issues, caching strategies, authorization…
whodb
Query and explore databases via MCP. Use when the user asks to inspect schemas, run SQL, browse tables, analyze data quality, generate ER diagrams, or work with PostgreSQL, MySQL, MariaDB, TiDB, SQLite, MongoDB, Redis, ClickHouse, Elasticsearch, or DuckDB.
graphjin-eval
Create, extend, run, baseline, and diagnose GraphJin agent evaluations through the graphjin eval CLI.