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/recapnpx skills add sharpdeveye/maestro --skill recapgit 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 | $0.00022 | $0.00564 |
| Opus 5 | $0.00011 | $0.00282 |
| Sonnet 5 | $0.00004 | $0.00113 |
| Haiku 4.5 | $0.00002 | $0.00056 |
Grade A, and why
recap 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 — 68 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.
Get back up to speed fast. Recap reads the most recent session file and recent decisions to tell you where you left off and what to do next.
Data Sources
.maestro/sessions/— read the most recent session file (by filename date).maestro/decisions.jsonl— read the last 5 decisions
If no session files exist, read the last 10 decisions and summarize those instead.
If no data exists at all, respond: "No session history found. Run /capture at the end of your next session to start tracking."
Output Format
┌─────────────────────────────────────┐
│ LAST SESSION RECAP │
├─────────────────────────────────────┤
│ Date: YYYY-MM-DD │
│ Commands: /diagnose → /fortify (2) │
│ Files: 3 changed, 1 created │
│ Outcome: Completed │
├─────────────────────────────────────┤
│ PICK UP HERE: │
│ 1. Run /guard — rate limiting │
│ 2. Run /evaluate — adversarial tests│
└─────────────────────────────────────┘
Recap Rules
- Be concise — this is a 30-second read, not a report
- Lead with the "PICK UP HERE" section — that's what the user needs
- If the session ended with open issues, highlight them
- Reference specific files and commands, not vague summaries
Recap Checklist
- Most recent session identified
- Commands and outcomes summarized in one line each
- "Pick up here" section has specific, actionable next steps
- Open issues from last session surfaced
Recommended Next Step
After recapping, run the first command listed in "Pick Up Here" to continue where you left off.
NEVER:
- Dump the entire session file — summarize it
- Recap without checking decisions.jsonl for recent activity
- Give vague next steps ("continue working") — be specific
- Assume context from the current conversation — only use persisted data
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 · 68 lines · 22 tokens per session scan A 3da54be44c53
recap is a skill published in the GitHub repository sharpdeveye/maestro (415 stars, last pushed 4mo ago), licensed MIT. It adds 22 tokens to every session and 564 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.
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.
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 /…
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…