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.
curl -O https://raw.githubusercontent.com/senda-labs/DQIII8/main/.claude/skills/mobilize/SKILL.mdgit clone --depth 1 https://github.com/senda-labs/DQIII8Wrote 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.
[](https://agentmods.dev/skills/senda-labs/dqiii8/mobilize)<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.
<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>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.
| Model | Per session | Once 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 |
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.
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)
- Enter plan mode immediately.
- Break the goal into sub-tasks, one per domain/concern.
- Write decomposition to
tasks/todo.mdunder Queued. - Write agent assignments to
tasks/status.md(format below). - 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.mdas agents complete. - If an agent fails or times out, note in
tasks/status.mdand 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.mdfrom Queued/In Progress → Done. - 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.
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.
- 11d ago First seen · 66 lines · 37 tokens per session scan A 99d8c6c8b611
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.
Other skills, from other repositories
using-adaptive-harness
Auto-mode bootstrap for adaptive-harness. Intercepts tasks, routes to optimal harness, evaluates results. Use on every task when adaptive-harness auto-mode is active.
task-taxonomy
Reference for the 6-axis task taxonomy used by adaptive-harness routing. Use when user asks how tasks are classified.
harness-registry
Manage the adaptive-harness pool: list, inspect, promote, demote harnesses. Use when user asks about harness status or wants to manage the pool.
skill-review-response
Use when a reviewer, CI bot, or another AI leaves feedback to address.
sys-configure
Configure Claude Octopus — redirects to /octo:setup interactive wizard.
continuum-tools-mcp
Connect MCP servers (Stdio/SSE/StreamableHTTP) to a Continuum agent, configure tool filtering, set up tool-context capture/injection (e.g. sessionid), and read run artifacts (UI widgets, structured tool data). Invoke when the user asks "connect MCP", "filesystem tool", "remote API tool", "auto-capture sessionid"…