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/chainnpx skills add sharpdeveye/maestro --skill chaingit 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 | $0.00024 | $0.00602 |
| Opus 5 | $0.00012 | $0.00301 |
| Sonnet 5 | $0.00005 | $0.00120 |
| Haiku 4.5 | $0.00002 | $0.00060 |
Grade A, and why
chain 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 yesterday.
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 — 72 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 tool-orchestration reference in the agent-workflow skill for composition patterns and error handling.
Design tool chains that do complex work reliably. A chain is only as strong as its weakest link.
Chain Patterns
Sequential: A → B → C (each step depends on the previous) Parallel: [A, B, C] → Merge (independent steps run simultaneously) Conditional: A → (if X then B, else C) → D (branching based on results) Iterative: A → Check → (if not done) → A again (loop until convergence)
Chain Design Process
For each chain, define:
## Chain: [Name]
### Steps
1. [Tool A] — [what it does] — Input: [schema] — Output: [schema]
2. [Tool B] — [what it does] — Input: [output of step 1] — Output: [schema]
3. [Tool C] — [what it does] — Input: [output of step 2] — Output: [schema]
### Data Flow
Step 1 output.field_a → Step 2 input.source_data
Step 2 output.results → Step 3 input.items
### Error Handling
Step 1 failure → [retry 3x, then return error]
Step 2 failure → [return partial results from step 1]
Step 3 failure → [retry with simplified input]
### Constraints
Max total execution time: 60s
Max retries per step: 3
Chain Validation
- Data schemas are compatible between connected steps
- Every step has error handling
- Total chain timeout is set
- Maximum iteration count is set for loops
- Partial results are handled (what if step 2 of 4 fails?)
Recommended Next Step
After building the chain, run /fortify to add error handling at each step, then /evaluate to test the full pipeline.
NEVER:
- Build chains without defining data contracts between steps
- Create loops without maximum iteration counts
- Skip error handling at any step (the chain breaks at the weakest link)
- Assume output of step N is always valid input for step N+1
- Build long chains when a single prompt could handle the task
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.
- yesterday First seen · 72 lines · 24 tokens per session scan A 8c0bd8954ba2
chain is a skill published in the GitHub repository sharpdeveye/maestro (415 stars, last pushed 4mo ago), licensed MIT. It adds 24 tokens to every session and 602 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.
skill-creator
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
agnt-plugin-builder
End-to-end workflow for creating, building, installing, and hot-reloading AGNT plugins entirely from chat. Use this skill whenever the user asks to 'build a plugin', 'create an AGNT plugin', 'add a new tool to AGNT', 'integrate X with AGNT' (where X is an API or service), 'make a plugin for [service]', or wants to…
annie-universal-api-orchestrator
Use AGNT's stored OAuth tokens and API keys to call ANY third-party API directly from the orchestrator, without building a tool or plugin first. Use this skill whenever the user asks you to "do something with my GitHub / Gmail / Drive / Slack / Notion / Stripe / Shopify / Discord / Linear / Jira / Vercel / Netlify /…
frontend-slides
Create stunning, animation-rich HTML presentations from scratch or by converting PowerPoint files. Use when the user wants to build a presentation, convert a PPT/PPTX to web, or create slides for a talk/pitch. Helps non-designers discover their aesthetic through visual exploration rather than abstract choices.
image-to-cinematic-video
Turn a prompt or an existing image into a polished multi-scene cinematic short video using Seedance for clip generation, uguu.se for file hosting, and FFmpeg for last-frame extraction and crossfade stitching. Supports two modes — PARALLEL (multiple scenes from the same reference image, concurrent, 3 min total) and…