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/sharpdeveye/maestro/adapt-workflownpx skills add sharpdeveye/maestro --skill adapt-workflowgit clone --depth 1 https://github.com/sharpdeveye/maestroWhat 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 | $0.00026 | $0.00504 |
| Opus 5 | $0.00013 | $0.00252 |
| Sonnet 5 | $0.00005 | $0.00101 |
| Haiku 4.5 | $0.00003 | $0.00050 |
Grade A, and why
adapt-workflow 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 — 62 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. Additionally gather: what the workflow is being adapted to.
Adapt a working workflow for a different context.
Adaptation Assessment
| Dimension | Current | Target | Impact |
|---|---|---|---|
| Model provider | ? | ? | Prompt format, capabilities, pricing |
| Model tier | ? | ? | Context window, reasoning ability |
| Deployment env | ? | ? | Latency, availability, compliance |
| Team structure | ? | ? | Monitoring, escalation, ownership |
| Data sensitivity | ? | ? | Guardrails, logging, access controls |
Provider Adaptation
- Prompt format: Adjust for provider-specific features
- Context limits: Resize context budget for different window sizes
- Capability gaps: Identify features available in one provider but not another
- Pricing model: Recalculate cost estimates
- API differences: Update tool calling interfaces, error handling, retry logic
Environment Adaptation
- Latency requirements: Adjust timeout values, caching strategy
- Compliance: Add or adjust guardrails, logging, and data handling
- Scale: Adjust concurrency limits, batch sizes
- Monitoring: Adapt alerting thresholds
Adaptation Checklist
- All provider-specific APIs updated
- Context budget recalculated for target model
- Cost estimates updated with target pricing
- Guardrails adjusted for target compliance requirements
- Tests updated and passing in target environment
- Documentation updated for target team
Recommended Next Step
After adaptation, run /evaluate to verify the workflow performs correctly in the target environment, then /diagnose for a full health check.
NEVER:
- Assume prompts work identically across providers
- Copy production config to development without adjusting guardrails
- Adapt without updating the evaluation suite
- Skip cost re-estimation
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 · 62 lines · 26 tokens per session scan A cb17c9c406a0
adapt-workflow is a skill published in the GitHub repository sharpdeveye/maestro (415 stars, last pushed 4mo ago), licensed MIT. It adds 26 tokens to every session and 504 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 skills, from other repositories
agent-self-scheduling
Schedule AI agent runs with cron, loops, or external clocks while avoiding unsafe tight autonomous timers.
sync-multica
Safely synchronize this repository's company constitution, Profession Profiles, Agent Instances, and persistent Squad topology to Multica, then prove the deployed state converges.
skill-creator
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Codex's capabilities with specialized knowledge, workflows, or tool integrations.
agent-harness-fault-injection
Use when an agent workflow needs deterministic recovery evidence for sandbox, MCP/tool, worker, checkpoint, memory, or orchestration failures.
agent-framework-azure-ai-py
Build persistent agents on Azure AI Foundry using the Microsoft Agent Framework Python SDK.
agent-orchestrator
Meta-skill que orquestra todos os agentes do ecossistema. Scan automatico de skills, match por capacidades, coordenacao de workflows multi-skill e registry management.