DQIII8: Skill for Claude Code

.claude/skills/mobilize/SKILL.md

mobilize is a skill for Claude Code from senda-labs/DQIII8. It costs 37 tokens per session (572 once invoked), scanned A, original, MIT.

A coordination protocol for tasks covering at least three distinct areas of work. It breaks the goal into smaller assignments for specialist agents, runs them in separate workspaces, and combines their results.

In plain words
What is it for?
Use it to decompose a broad task, assign up to five specialist agents, monitor their result files, retry a failed agent once, and aggregate the completed findings.
Why use it?
It organizes complex cross-area work so each part can be handled independently while the main agent tracks progress and failures.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions subagents.

This is senda-labs/DQIII8's own configuration. It tells Claude Code how to work on DQIII8 itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything DQIII8 configures →

Part of the dqiii8 plugin — 22 skills, 14 commands, 17 agents shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to senda-labs/DQIII8. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/senda-labs/DQIII8/main/.claude/skills/mobilize/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/senda-labs/DQIII8

Made for: Claude Code.

Or install dqiii8, the plugin that ships this one along with the rest of its 22 skills, 14 commands, 17 agents.

Wrote 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.

agentmods badge for mobilize

README.md
[![agentmods](https://agentmods.dev/badge/skills/senda-labs/dqiii8/mobilize/github.svg)](https://agentmods.dev/skills/senda-labs/dqiii8/mobilize)
Your own site
<a href="https://agentmods.dev/skills/senda-labs/dqiii8/mobilize"><img src="https://agentmods.dev/badge/skills/senda-labs/dqiii8/mobilize/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.

agentmods 80×15 button for mobilize

Your own site · 80×15
<a href="https://agentmods.dev/skills/senda-labs/dqiii8/mobilize"><img src="https://agentmods.dev/badge/skills/senda-labs/dqiii8/mobilize.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 572 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00037 $0.00572
Opus 5 $0.00018 $0.00286
Sonnet 5 $0.00007 $0.00114
Haiku 4.5 $0.00004 $0.00057

Measured 11d ago against content hash 99d8c6c8b611, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

mobilize 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 11d 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.

.claude/skills/mobilize/SKILL.md · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/mobilize — Multi-Agent Coordination Protocol

Trigger Conditions

  • User invokes /mobilize
  • User says "coordinate" + describes 3+ distinct domains
  • Task touches 3+ unrelated domains simultaneously

Protocol

Step 1 — Decompose (Orchestrator, Plan Mode)

  1. Enter plan mode immediately.
  2. Break the goal into sub-tasks, one per domain/concern.
  3. Write decomposition to tasks/todo.md under Queued.
  4. Write agent assignments to tasks/status.md (format below).
  5. Maximum 5 parallel agents.

Step 2 — Spawn Agents

For each sub-task:

  • Spawn a Task agent with the appropriate agent type (see .claude/rules_db/common/agents.md § Two runtimes, two SSOTs).
  • Pass only the minimum context needed for that sub-task.
  • Every agent gets an isolated worktree (isolation: worktree).
  • Each agent writes its result to tasks/results/{agent_name}-{YYYY-MM-DD}.md.
  • Agents NEVER write to tasks/todo.md.

Step 3 — Monitor

  • Poll tasks/results/ until all expected result files appear.
  • Update tasks/status.md as agents complete.
  • If an agent fails or times out, note in tasks/status.md and re-spawn once.

Step 4 — Aggregate

  • Read all result files from tasks/results/.
  • Synthesize into a final summary for the user.
  • Move completed tasks in tasks/todo.md from Queued/In ProgressDone.
  • Clean up tasks/status.md.

tasks/status.md Format

# Mobilize Status — {goal summary}
Started: {timestamp}

| Agent | Sub-task | Status | Result file |
|-------|----------|--------|-------------|
| python-specialist | Refactor X | done | tasks/results/python-specialist-2026-03-11.md |
| code-reviewer | Review PR | running | — |

Constraints

  • Max 5 parallel agents.
  • Each agent: isolated worktree at /tmp/dqiii8-wt/{agent_id}.
  • Orchestrator does NOT share its context window with subagents.
  • Destructive actions always require user confirmation before spawning agents.
  • If decomposition is unclear, ask the user ONE clarifying question before proceeding.

Read the full file on GitHub · 66 lines

Changes

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.

  1. 11d ago First seen · 66 lines · 37 tokens per session scan A 99d8c6c8b611

Subscribe to this mod's changes

mobilize is a skill published in the GitHub repository senda-labs/DQIII8 (11 stars, last pushed 23d ago), licensed MIT. It adds 37 tokens to every session and 572 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.