A command that assigns open Speckit tasks to active Squad agents according to their skills or a configured rotation. Speckit is the project's system for specifications and task lists.

Use it after creating a task list to add agent assignments and routing information to the tasks.

It prevents tasks from remaining unassigned or going to an unsuitable agent.

route — Command by sabbour

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods

npx agentmods add commands/sabbour/agentweaver/route

Clone the repo

git clone --depth 1 https://github.com/sabbour/agentweaver

Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 761 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

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.

Model	Per session	Once invoked
Fable 5	$0.00014	$0.00761
Opus 5	$0.00007	$0.00380
Sonnet 5	$0.00003	$0.00152
Haiku 4.5	$0.00001	$0.00076

Measured 2d ago against content hash 1d6f7bd14f67, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

route 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 2d 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.

.specify/extensions/squad/commands/route.md · 84 lines

How it starts

The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Squad Bridge: Route Tasks

Read open tasks from the Speckit task list and assign each to the most appropriate Squad agent using capability matching or round-robin (configured in squad-config.yml).

This command is also triggered by the after_tasks hook.

User Input

$ARGUMENTS

Steps

Verify prerequisites:
- specs/<id>/tasks.md exists; if not, tell the user to run /speckit.tasks first and stop.
- .squad/ exists; if not, tell the user to run /speckit.squad.init first and stop.
Load bridge config from .specify/extensions/squad/squad-config.yml if it exists, otherwise use extension defaults.
Read open tasks from specs/<id>/tasks.md. Parse each task's title, description, and any tags or phase labels.
Load Squad agents and routing rules from .squad/ (agents directory and routing.md). Only consider agents with status: active.
Route each task using the configured routing_strategy:

capability-match (default):
- Extract domain keywords from the task title and description
- Match against agent capabilities using the routing rules in .squad/routing.md
- If multiple agents match, prefer the one with the highest capability level for the matched domain
- If no agent matches, assign to coordinator and flag for manual review
round-robin:
- Assign tasks to active agents in a rotating sequence
- Track assignment counts to ensure even distribution
Determine model tier for each task:
- Tasks involving architecture decisions, complex algorithms, or spec interpretation → full tier
- Standard feature implementation → standard tier
- Boilerplate, scaffolding, documentation → lightweight tier

Output a routing table:

Task Routing Summary
─────────────────────────────────────────────────────────────────────
Task                                  Agent               Tier
─────────────────────────────────────────────────────────────────────
Design REST API endpoints             backend-engineer    full
Implement JWT authentication          backend-engineer    standard
Build login form component            frontend-engineer   standard
Write unit tests for auth service     qa-engineer         standard
Set up GitHub Actions CI pipeline     devops-engineer     standard
Add README and API docs               ⚠️ coordinator      lightweight
─────────────────────────────────────────────────────────────────────
Routed: 5 / 6   Unrouted (needs review): 1

Read the full file on GitHub · 84 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.

2d ago First seen · 84 lines · 14 tokens per session scan A 1d6f7bd14f67

Subscribe to this mod's changes

route is a command published in the GitHub repository sabbour/agentweaver (5 stars, last pushed 2d ago), licensed MIT. It adds 14 tokens to every session and 761 once invoked, about $0.0001 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 2026-08-31.

Building agents Project management agent-orchestration ai-agents aks dotnet human-in-the-loop kubernetes

go

Approve session plan and begin wave execution.

Kanevry/session-orchestrator · 7 tokens

self-improve

Bootstrap and operate a self-improving agent workspace. Scaffolds .learnings/ and memory/ directories, captures errors and learnings during a session, detects recurring patterns, and promotes stable entries to project memory (CLAUDE.md, AGENTS.md, or references/). Also implements the Proactive Agent pillars — WAL…

nitinjain999/platform-skills · 137 tokens

route