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 timurgaleev/memex --skill minion-orchestratorgit clone --depth 1 https://github.com/timurgaleev/memexWrote 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/timurgaleev/memex/minion-orchestrator)<a href="https://agentmods.dev/skills/timurgaleev/memex/minion-orchestrator"><img src="https://agentmods.dev/badge/skills/timurgaleev/memex/minion-orchestrator/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/timurgaleev/memex/minion-orchestrator"><img src="https://agentmods.dev/badge/skills/timurgaleev/memex/minion-orchestrator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 238 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 239 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00069 | $0.02154 |
| Opus 5 | $0.00034 | $0.01077 |
| Sonnet 5 | $0.00014 | $0.00431 |
| Haiku 4.5 | $0.00007 | $0.00215 |
Grade A, and why
minion-orchestrator 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 9d 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 — 253 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Minion Orchestrator
Contract
"Minions" here means durable background work. memex ships a Postgres-native durable job queue for observable server-side work; agent-side reasoning fan-out uses the agent harness's own subagents (e.g. the Claude Code Task tool). This single skill handles both lanes:
- Deterministic server jobs (
jobs_submit/memex jobsfrom the shell) - LLM subagent work (the agent's own subagent runtime)
When to route to the durable queue: work that must survive restarts, be observable across sessions, or run without the agent staying attached. The default policy is pain-triggered: use the agent's native subagents first, reach for durable jobs when a specific pain signal fires (restart loss, long runtime, needs later inspection).
Guarantees (durable lane):
- Jobs survive server restart (Postgres-backed)
- Every job has structured progress and per-job logs
- Jobs can be cancelled at any time, and retried after failure
- Progress is queryable without loading the full job record
Not guaranteed: mid-flight steering, pause/resume. The queue is
cancel-and-resubmit — if a job's direction is wrong, jobs_cancel it and
submit a corrected one.
Route the Request: Server Job vs Subagent
| Condition | Action |
|---|---|
| User asks for deterministic command/script run | Server job (shell lane, operator CLI) |
| User asks for reindex / embed backfill / maintenance sweep | Server job (jobs_submit, or the corresponding memex CLI command) |
| User asks for research/reasoning/iterative agent work | Agent-side subagent (harness Task tool) |
| User asks to cancel/retry running work | jobs_cancel / retry_job |
| Single simple operation under ~30s | Consider inline execution first |
| Needs restart durability/observability | Submit as a durable job |
| Parallel work (2+ streams) | Agent-side subagent fan-out; each child reads/writes the brain over MCP |
If intent is ambiguous, ask one clarification: "Do you want a deterministic server job, or agent-side LLM work?"
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.
- 9d ago First seen · 253 lines · 69 tokens per session scan A 2361fd82500e
minion-orchestrator is a skill published in the GitHub repository timurgaleev/memex (8 stars, last pushed today), licensed MIT. It adds 69 tokens to every session and 2,154 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
gbrain-briefing
Compile a daily briefing from brain state. Covers active deals, open threads, people in play, and what needs attention.
wiki-dashboard
Create dynamic, queryable dashboard views of the Obsidian vault using Obsidian Bases or Dataview. Use this skill when the user says "create a dashboard", "vault dashboard", "show all X as a table", "dynamic view", "query my vault", "build a content index", "show me all concepts/entities/projects", or wants a…
daily-update
Run the daily wiki maintenance cycle: check all source freshness, update the index, and regenerate hot.md. Use this skill when the user says "/daily-update", "run the daily update", "update everything", "morning sync", "refresh the wiki index", or when triggered by the launchd cron at 9 AM. Also use to set up or…
design-mcp-server
Design the tool surface, resources, and service layer for a new MCP server. Use when starting a new server, planning a major feature expansion, or when the user describes a domain/API they want to expose via MCP. Produces a design doc at docs/design.md that drives implementation.
api-canvas
DataCanvas primitive reference — a Tier 3 SQL/analytical workspace for tabular MCP servers, backed by DuckDB. Use when registering tables from upstream APIs, running ad-hoc SQL across them, and exporting results. Covers the acquire → register → query → export flow, per-table TTL, the token-sharing pattern for…
maintenance
Investigate, adopt, and verify dependency updates — with special handling for @cyanheads/mcp-ts-core. Captures what changed, understands why, cross-references against the codebase, adopts framework improvements, syncs project skills, and runs final checks. Supports two entry modes: run the full flow end-to-end, or…