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/rafmacalaba/armada/armada-dispatchnpx skills add rafmacalaba/armada --skill armada-dispatchgit clone --depth 1 https://github.com/rafmacalaba/armadaWhat 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 | $0.00047 | $0.00378 |
| Opus 5 | $0.00023 | $0.00189 |
| Sonnet 5 | $0.00009 | $0.00076 |
| Haiku 4.5 | $0.00005 | $0.00038 |
Grade A, and why
armada-dispatch 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.
What it actually says
Armada: Parallel Subagent Dispatch
When two or more tasks are independent, dispatch them as parallel subagents. The key constraint: parallel tasks must write disjoint files. Shared files force serialization.
Rules
- Build a dependency graph from the phase list. Independent phases (no shared deps) can run in parallel.
- Check file scope: two phases can run in parallel only if they never write the same file. Prefer per-phase file isolation (e.g.
src/<feature>.js+ its test). - Backend-dev and frontend-dev within the same phase can run in parallel when the API contract is fixed first, since they write different source trees.
- Wait for all dispatched subagents to return before gating the phase. Do not end your turn with background work outstanding.
- When NOT to parallelize: shared output file, sequential dependency between tasks, or one task's output is the other's input. Serialize writers on a reused subagent session.
Example: Phase 2 (API) and Phase 3 (UI) are independent and write src/api/ vs src/ui/ — dispatch both as parallel background subagents.
Adaptive roster
- Infer risk from changed surface; keep non-required roles standby.
- QA is always active. Low risk uses implementer + QA; high risk adds security and adversary, with architect for shared or cross-cutting design.
- Separate voyages use separate worktrees and run concurrently. Return compact receipts with
Status,Files,Evidence,Result,Risks, andNext.
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 · 27 lines · 0 tokens per session scan A d381e994bb56
armada-dispatch is a skill published in the GitHub repository rafmacalaba/armada (91 stars, last pushed 4d ago), licensed MIT. It adds 47 tokens to every session and 378 once invoked, about $0.0002 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
aoe
Use when launching, monitoring, or controlling AI coding agents (Claude Code, Codex, OpenCode, etc.) in tmux via Agent of Empires (aoe). Covers creating sessions, capturing agent output, running parallel worktree agents, and organizing work into groups and profiles. Prefer aoe over raw tmux for agent management.
aoe
Manage AI coding agent sessions via Agent of Empires (aoe).
debate
Structured adversarial analysis protocol. Quick single-agent modes (challenge, panel, pre-mortem, red team) plus a decision-review protocol where one agent proposes, one critiques, the proposer revises, and a binding/advisory judge panel decides ADOPT/REVISE/REJECT/ESCALATE.
update-to-latest
Safety-critical operational pipeline for analyzing and executing OpenCode/OMO updates with explicit approval, patch preservation, rollback capability, and evidence-state discipline.
reader-report
Reader-first writing for any deliverable a human reads to understand a result: HTML reports, MD design docs, debate-result summaries, survey dashboards, executive briefs, handoff notes, panel-review syntheses. Writes for a reader who has NOT read the preceding material. NOT for: bug reports, incident reports, status…
patch-tracker
Track and verify custom patches to external dependencies. Register, audit, and verify patches survive updates. CRUD lifecycle for patch entries with post-update verification.