From 7ec0b7d35b9203cc6a86c1d0fc3916a05023800e Mon Sep 17 00:00:00 2001 From: vp Date: Tue, 3 Mar 2026 10:58:18 +0300 Subject: [PATCH 1/2] super-swarm-spark: unify concurrency docs to 15 and add max_threads note --- skills/super-swarm-spark/SKILL.md | 22 +++++++++++++++------- 1 file changed, 15 insertions(+), 7 deletions(-) diff --git a/skills/super-swarm-spark/SKILL.md b/skills/super-swarm-spark/SKILL.md index f41ea63..bc9b5b3 100644 --- a/skills/super-swarm-spark/SKILL.md +++ b/skills/super-swarm-spark/SKILL.md @@ -4,7 +4,7 @@ description: > Only to be triggered by explicit super-swarm-spark commands. --- -# Parallel Task Executor (Sparky Rolling 12-Agent Pool) +# Parallel Task Executor (Sparky Rolling 15-Agent Pool) You are an Orchestrator for subagents. Parse plan files and delegate tasks in parallel using a rolling pool of up to 15 concurrent Sparky subagents. Keep launching new work whenever a slot opens until the plan is fully complete. @@ -53,11 +53,11 @@ Rules: - Require explicit file targets in every subagent assignment. - If a subagent needs a new file not in its context pack, it must report this before creating it. -### Step 4: Launch Subagents (Rolling Pool, Max 12) +### Step 4: Launch Subagents (Rolling Pool, Max 15) Run a rolling scheduler: - States: `pending`, `running`, `completed`, `failed` -- Launch up to 12 tasks immediately (or fewer if less are pending) +- Launch up to 15 tasks immediately (or fewer if less are pending) - Whenever any running task finishes, validate/update plan for that task, then launch the next pending task immediately - Continue until no pending or running tasks remain @@ -66,7 +66,7 @@ For each launched task, use: - **description**: "Implement task [ID]: [name]" - **prompt**: Use template below -Do not wait for grouped batches. The only concurrency limit is 12 active Sparky subagents. +Do not wait for grouped batches. The only concurrency limit is 15 active Sparky subagents. Every launch must set `agent_type: sparky`. Any other role is invalid for this skill. @@ -154,11 +154,19 @@ Completion bar: ## Scheduling Policy (Required) -- Max concurrent subagents: **12** -- If pending tasks exist and running count is below 12: launch more immediately +- Max concurrent subagents: **15** +- If pending tasks exist and running count is below 15: launch more immediately - Do not pause due to relationship metadata - Continue until the full plan (or requested subset) is complete and integrated +If runtime limits prevent reaching 15 active agents, increase Codex thread allowance: + +`~/.codex/config.toml` +```toml +[agents] +max_threads = 16 +``` + ## Error Handling - Task subset not found: List available task IDs @@ -182,7 +190,7 @@ Completion bar: ## Tasks Assigned: [N] ## Concurrency -- Max workers: 12 +- Max workers: 15 - Scheduling mode: rolling pool (continuous refill) ### Completed From 063a2ed66911eb423b3278ee1f791973999892e7 Mon Sep 17 00:00:00 2001 From: vp Date: Tue, 3 Mar 2026 11:00:13 +0300 Subject: [PATCH 2/2] super-swarm-spark: clarify thread allowance includes orchestrator --- skills/super-swarm-spark/SKILL.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/skills/super-swarm-spark/SKILL.md b/skills/super-swarm-spark/SKILL.md index bc9b5b3..1f24945 100644 --- a/skills/super-swarm-spark/SKILL.md +++ b/skills/super-swarm-spark/SKILL.md @@ -159,7 +159,7 @@ Completion bar: - Do not pause due to relationship metadata - Continue until the full plan (or requested subset) is complete and integrated -If runtime limits prevent reaching 15 active agents, increase Codex thread allowance: +If runtime limits prevent reaching 15 active agents plus orchestrator, increase Codex thread allowance: `~/.codex/config.toml` ```toml