Skip to content

mattvideoproductions/MVP-Prompts / skills/foreman

foreman

Verified

Be the foreman on a big job. One lead model plans the work, hands pieces to helper agents in lanes that never share files, checks everything before accepting it and reports the cost; or runs a long solo build with an owner in the loop. Covers the North Star plan of record, briefs that carry the lead's reasoning, measured gates plus the owner's judgement, strike-based promotion between model tiers, a cost ledger and a mistake register every pass is checked against. Use it when the user types /foreman, says "be the foreman", "be the lead" or "orchestrate this", asks to delegate to subagents or run lanes or passes, or mentions a North Star, three strikes, tiers or promotion between models. Also load it when a task looks too big for one context or needs several agents or days, even if not asked by name; the skill then has you offer it and wait for a yes. Also use it to resume such a project, close a pass, report a session's cost or record a mistake. Not for a change one agent can finish in one sitting.

assets/config.default.json

View on GitHub
{
  "started_at": null,
  "pass_cap": null,
  "budget_usd": null,
  "transcripts": [],
  "not_counted": [],
  "context_budget_tokens": 200000,
  "lead_context_budget_tokens": 300000,
  "idle_gap_minutes": 5,
  "rewrite_min_tokens": 50000,
  "rewrite_share_ask_above": 0.15,
  "senior_share_ask_above": 0.5,
  "cache_read_share_ask_above": 0.5,
  "current_state_max_lines": 15,
  "strike_allowance": {
    "light": 3,
    "standard": 2,
    "senior": 2,
    "lead": 3
  },
  "lesson_strike_limit": 3,
  "_notes": {
    "context_budget_tokens": "A worker whose context passes this should have handed off. Three field reports asked for a size budget in place of a turn count; 150-200K was the one figure offered. Untested.",
    "lead_context_budget_tokens": "Ask the lead to hand off to a fresh session past this. Leads in the field reached 966K. The number is a guess.",
    "idle_gap_minutes": "A context rewrite after a gap at least this long is counted as an idle rewrite. 5 is the shortest cache lifetime.",
    "rewrite_min_tokens": "Only contexts at least this large count as a rewrite when most of the prompt is written to the cache again.",
    "rewrite_share_ask_above": "Ask when rewriting context is more than this share of a pass's cost. One-hour cache writes were 23% and 50% of two leads' cost in the field. Guess.",
    "senior_share_ask_above": "Ask the lead to justify the pass when more than this share of worker responses came from the senior tier or above. Field values: 98%, 89%, 78%, 61%.",
    "cache_read_share_ask_above": "Ask when re-reading is more than this share of a pass's cost. Field values on worker tiers: 45% to 58%.",
    "strike_allowance": "The most strikes a lane may collect at a tier before it must move up. Three is the ceiling. A tier gets all three only when the next tier costs many times more (light to standard is 20x). At a 2x gap the default is to promote after the first strike and allow a second only when the first pass closed most of the gap. Retune when prices change.",
    "transcripts": "Extra transcript files or folders to count. Empty means the Claude Code folder for this project.",
    "not_counted": "Plain-language list of spend this ledger cannot see, e.g. 'Codex lane, billed by another vendor'. Printed on every cost line."
  }
}
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 471kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall