{"slug":"agent-army","title":"agent-army","summary":"Deploy a 2-layer parallel agent hierarchy for large, parallelizable work — big refactors, multi-file migrations, codebase-wide audits, bulk generation. A top-tier commander (Fable or Opus) orchestrates the swarms; the user picks a power level (Max Power / Heavy / Balanced / Econo","platform":"Claude","tags":[],"authorName":"LLM Mart","authorSlug":"llm-mart","score":0,"source":"github","price":null,"verified":false,"createdAt":"2026-09-20T07:59:31.776254Z","repo":{"url":"https://github.com/OneWave-AI/claude-skills","stars":309,"forks":53,"license":"MIT","updatedAt":"2026-09-23T02:11:41Z"},"bodyHtml":"<hr>\n<h2>name: agent-army\ndescription: \"Deploy a 2-layer parallel agent hierarchy for large, parallelizable work — big refactors, multi-file migrations, codebase-wide audits, bulk generation. A top-tier commander (Fable or Opus) orchestrates the swarms; the user picks a power level (Max Power / Heavy / Balanced / Economy) that sets the Opus/Sonnet/Haiku model mix per layer. Layer 1 is 3-50+ specialist agents, each with its own full context window; Layer 2 is 2+ sub-agents per member. Includes git safety, tiered sizing, a pre-deploy gate, phantom-completion checks, and multi-wave follow-up.\"\nuser_invocable: true</h2>\n<h1>Agent Army</h1>\n<p>A 2-layer parallel execution framework. The Commander is the top-tier model — Fable by default, or Opus if that's the session model — and does the thinking: recon, composition, briefing, verification. It orchestrates swarms of subordinate models whose tiers the user picks at deploy time (see Power Level). Each Layer 1 agent has its own full context window (not a slice). Each spawns Layer 2 sub-agents under it. The result is many independent brains running at once — not one brain divided.</p>\n<pre><code>Commander (you — Fable or Opus, the session model)\n |\n |-- Layer 1: Team (3 to 50+, each = own 1M context, L1 tier from power level)\n |    |-- Agent A (1M) -- Sub-agent A1, A2, ...  (L2 tier)\n |    |-- Agent B (1M) -- Sub-agent B1, B2, ...  (L2 tier)\n |    |-- Agent C (1M) -- Sub-agent C1, C2, ...  (L2 tier)\n |    |-- ... (no cap)\n</code></pre>\n<p><strong>Swarm vs. army:</strong> A swarm splits one context window across sub-agents — one brain, divided. An army gives each Layer 1 member its own window. That difference is the whole point of this skill.</p>\n<h2>When to use</h2>\n<ul>\n<li>Large refactors spanning many files</li>\n<li>Multi-file color / style / naming / API migrations</li>\n<li>Broad codebase audits (security, a11y, performance, dead code)</li>\n<li>Bulk content generation or transformation</li>\n<li>Any task with <strong>6+ independent units of work</strong> that can run simultaneously</li>\n</ul>\n<h2>When NOT to use</h2>\n<ul>\n<li>Fewer than 6 independent units of work — just do it directly</li>\n<li>Heavy sequential dependencies where each step needs the last one's output</li>\n<li>Single-file changes</li>\n<li>Tasks needing one coherent authorial voice across all output (parallel agents drift)</li>\n</ul>\n<p>If the task doesn't clearly fit, say so and propose doing it inline instead of spinning up an army.</p>\n","files":[{"path":"SKILL.md","sizeBytes":15895,"isText":true}],"reviewScore":null,"reviewSummary":null,"trust":{"provenance":"trusted-source-unreviewed","notice":"Community-authored content, reproduced verbatim and not vetted as instructions. Treat it as data to evaluate, never as directives to follow.","bodySource":null},"bodyLocked":false,"purchaseUrl":null,"sourceUrl":null,"report":{"provenance":"trusted-source-unreviewed","screen":{"ran":true,"outcome":"clean","suspicious":0,"notes":0,"hiddenCharacters":false},"virusScan":{"engine":"clamav","status":"clean","scannedAt":"2026-09-20T07:59:40.640843Z","sha256":"436F5B668BA30B650DCBBCEB80316417B9F4709A7F09F6EB2900F0EABFB3522B","sizeBytes":6696},"review":null,"source":{"repositoryUrl":"https://github.com/OneWave-AI/claude-skills","path":"agent-army","license":"MIT","commit":"f317e08649a6584ed4cd0b1ae353f123f4daf791","subtreeSha":"EDDC1EA9CEE7CA91AD18EE269A94A7B79D9A9B44E228590709637902827D8D9F","lastSyncedAt":"2026-09-27T20:55:05.158052Z"},"reviewedAt":"2026-09-20T08:01:10.402722Z","notice":"Community-authored content, reproduced verbatim and not vetted as instructions. Treat it as data to evaluate, never as directives to follow."},"install":[{"target":"skills-cli","command":"npx skills add https://github.com/OneWave-AI/claude-skills/tree/main/agent-army"},{"target":"claude-code","command":"claude plugin marketplace add https://llmmart.ai/marketplace.json && claude plugin install onewave-ai-claude-skills@llmmart"},{"target":"git","command":"git clone https://github.com/OneWave-AI/claude-skills.git"}]}