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 sharpdeveye/maestro --skill calibrategit clone --depth 1 https://github.com/sharpdeveye/maestroWrote 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/sharpdeveye/maestro/calibrate)<a href="https://agentmods.dev/skills/sharpdeveye/maestro/calibrate"><img src="https://agentmods.dev/badge/skills/sharpdeveye/maestro/calibrate/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/sharpdeveye/maestro/calibrate"><img src="https://agentmods.dev/badge/skills/sharpdeveye/maestro/calibrate.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 | $0.00027 | $0.00676 |
| Opus 5.5 | $0.00011 | $0.00270 |
| Sonnet 5.5 | $0.00005 | $0.00135 |
| Haiku 4.5 | $0.00003 | $0.00068 |
Grade A, and why
calibrate 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 1mo 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 — 85 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. Consult the prompt-engineering reference in the agent-workflow skill for naming and style consistency patterns.
Ensure consistency across all workflow components. Inconsistency creates confusion — for the model, for developers, and for users.
Calibration Dimensions
Naming Conventions
- Tool names follow consistent pattern (verb_noun, noun.verb, or camelCase — pick one)
- Agent names follow consistent pattern
- Configuration keys follow consistent pattern
- File names follow consistent pattern
Prompt Style
- All prompts use the same structural pattern (4-zone)
- Consistent delimiter style (XML tags, markdown headers, triple-dash)
- Consistent output schema format (JSON schema, markdown template)
- Consistent instruction style (imperative, numbered steps)
Error Handling
- All tools return errors in the same format
- Error codes follow consistent scheme
- Error messages follow consistent tone
- Retry logic uses consistent strategy
Logging
- All logs use the same format (JSON structured, text, etc.)
- Consistent field names across all log entries
- Consistent log levels (debug, info, warn, error)
- Consistent PII redaction approach
Calibration Process
- Identify the standard: What's the most common pattern in the existing codebase? That's the standard.
- List deviations: Find all components that deviate from the standard.
- Prioritize: Fix the most impactful deviations first (user-facing > internal).
- Apply: Make the changes, ensuring tests still pass.
- Document: Update
.maestro.mdwith the established conventions.
Consistency Audit Table
| Dimension | Standard | Deviations Found | Priority |
|---|---|---|---|
| Tool naming | ? | ? of ? tools | High/Med/Low |
| Prompt structure | ? | ? of ? prompts | High/Med/Low |
| Error format | ? | ? of ? tools | High/Med/Low |
| Log format | ? | ? of ? entries | High/Med/Low |
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.
- 1mo ago First seen · 85 lines · 27 tokens per session scan A 823c4149ce52
calibrate is a skill published in the GitHub repository sharpdeveye/maestro (591 stars, last pushed 5mo ago), licensed MIT. It adds 27 tokens to every session and 676 once invoked, about $0.0001 per session on Opus 5.5. 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 skills, from other repositories
aider-delegate
Delegate coding tasks to Aider (aider) only when the user explicitly requests it, while the orchestrator retains review and landing responsibility.
agy-delegate
Delegate coding tasks to the Google Antigravity CLI (agy) only when the user explicitly requests it, while the orchestrator retains review and landing responsibility.
agent-self-scheduling
Schedule AI agent runs with cron, loops, or external clocks while avoiding unsafe tight autonomous timers.
deep-interview
Socratic deep interview with mathematical ambiguity gating before execution.
plan
Strategic planning with optional interview workflow.
web-clone
URL-driven website cloning with visual + functional verification.