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 capturegit 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/capture)<a href="https://agentmods.dev/skills/sharpdeveye/maestro/capture"><img src="https://agentmods.dev/badge/skills/sharpdeveye/maestro/capture/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/capture"><img src="https://agentmods.dev/badge/skills/sharpdeveye/maestro/capture.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 | $0.00022 | $0.00617 |
| Opus 5.5 | $0.00009 | $0.00247 |
| Sonnet 5.5 | $0.00004 | $0.00123 |
| Haiku 4.5 | $0.00002 | $0.00062 |
Grade A, and why
capture 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 — 80 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.
Capture the current session's work into a persistent summary. This creates a record that survives session boundaries — future commands can reference what happened here.
What to Capture
Read the conversation history and identify:
- Commands run — which Maestro commands were invoked and in what order
- Decisions made — architectural choices, trade-offs accepted, patterns adopted
- Files changed — what was created, modified, or deleted
- Issues found — bugs, gaps, or risks identified
- Next steps — what should happen next (be specific)
Output Format
Generate a session summary file at .maestro/sessions/{date}_{topic}.md:
# Session: {topic}
Date: {YYYY-MM-DD}
## Commands Run
- /diagnose → Score: 18/25
- /fortify → Added retry logic to API handlers
- /evaluate → Verified with 3 test scenarios
## Decisions
- Chose retry-with-backoff over circuit breaker (simpler, sufficient for current load)
- Kept synchronous error handling (async not justified yet)
## Files Changed
- `src/api/handler.ts` — added retry wrapper
- `src/middleware/auth.ts` — added input validation
- `tests/api.test.ts` — new test file
## Open Issues
- Rate limiting not yet implemented (deferred to next session)
## Next Steps
1. Run `/guard` to add rate limiting
2. Run `/evaluate` with adversarial test cases
Also append a decision entry to .maestro/decisions.jsonl recording this capture.
Session Capture Checklist
- All commands from this session listed
- Key decisions documented with rationale
- Files changed listed with brief descriptions
- Open issues captured (nothing lost)
- Next steps are specific and actionable
- Summary saved to
.maestro/sessions/
Recommended Next Step
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 · 80 lines · 22 tokens per session scan A 94afa951f7b2
capture is a skill published in the GitHub repository sharpdeveye/maestro (591 stars, last pushed 5mo ago), licensed MIT. It adds 22 tokens to every session and 617 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
wiki-ingest
Use when an operation issue asks to ingest a captured raw/ source into the LLM Wiki, or the user says "ingest ". Create durable source, entity, concept, synthesis, index, and log pages; use paperclip-distill for Paperclip bundles.
wiki-lint
Use when an LLM Wiki operation issue is a lint or health check. Audit for contradictions, orphans, weak provenance, broken links, missing concept pages, and index/log drift; return triage findings without auto-fixing.
aider-delegate
Delegate coding tasks to Aider (aider) only when the user explicitly requests it, while the orchestrator retains review and landing responsibility.
agent-memory-discipline
Rules for when an agent should recall from long-term memory before acting and when it should save decisions, corrections and failures afterwards. Works with any memory backend.
agent-self-scheduling
Schedule AI agent runs with cron, loops, or external clocks while avoiding unsafe tight autonomous timers.
agent-memory
A hybrid memory system that provides persistent, searchable knowledge management for AI agents.