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 commands/pydantic/skills/querygit clone --depth 1 https://github.com/pydantic/skillsWhat 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 | $0.00015 | $0.01222 |
| Opus 5 | $0.00008 | $0.00611 |
| Sonnet 5 | $0.00003 | $0.00244 |
| Haiku 4.5 | $0.00002 | $0.00122 |
Grade A, and why
query 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 2d 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/query
Help users query traces, logs, and metrics from Logfire. Supports two approaches: interactive querying via the MCP server, or adding programmatic query capabilities to code.
Prerequisites
One of the following:
- MCP: Logfire MCP server connected (this plugin configures it automatically). User must have run
logfire author setLOGFIRE_TOKEN. - REST API: A Logfire read token (created via the Logfire UI or
logfire read-tokens create).
Workflow
Route the request first
Use /query only when the user wants data fetched and analyzed, a SQL query, a computed answer, or programmatic query code.
Do not use /query for direct UI/browser/link requests such as "open in Logfire", "show in Codex", "open Explore", "live view", or "give me a link". Route those to logfire-ui.
For ambiguous prompts such as "show recent errors", "view logs", or "show spans", ask whether the user wants a Logfire UI view or query analysis in chat. Do not do both unless the user explicitly asks for both.
Determine the approach
Ask the user what they need:
- Explore data interactively — they want to search traces, investigate issues, or understand their telemetry. Use MCP.
- Add querying to code — they want their application to query Logfire programmatically. Use the REST API / Python client.
If unclear, default to interactive (MCP) since it requires no extra setup.
Interactive querying (MCP)
-
Understand what the user is looking for. Ask clarifying questions if needed: time range, service name, error type, endpoint, trace ID, etc.
-
Formulate the SQL query. Use Apache DataFusion SQL (Postgres-like). Always follow these rules:
- Always include
LIMIT(start with 20, increase if needed) - Filter by
start_timestampfor time ranges:start_timestamp > now() - interval '1 hour' - Filter by
service_name,span_name, ortrace_idwhen possible for efficiency - Use
min_timestamp/max_timestampparams instead of SQLWHEREfor time filtering when the window is simple - Access JSON attributes with
->>'key'operator
- Always include
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.
- 2d ago First seen · 115 lines · 15 tokens per session scan A 6d82aaae1b9d
query is a command published in the GitHub repository pydantic/skills (127 stars, last pushed 2d ago), licensed MIT. It adds 15 tokens to every session and 1,222 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.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.