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.
npx agentmods add commands/nxtg-ai/forge-plugin/agent-assigngit clone --depth 1 https://github.com/nxtg-ai/forge-pluginWhat 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 | $0.00000 | $0.01265 |
| Opus 5 | $0.00000 | $0.00633 |
| Sonnet 5 | $0.00000 | $0.00253 |
| Haiku 4.5 | $0.00000 | $0.00127 |
Grade A, and why
agent-assign 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 3d 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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/forge:agent-assign
Intelligently match tasks to the best specialized agent by analyzing task domain, complexity, and required skills, then launch the agent to execute autonomously.
| Level | L1 Vibe Coder |
| Category | Feature Development |
| Syntax | /forge:agent-assign [task description] [--list] [--auto] [--agent <name>] |
What It Does
/forge:agent-assign is the intelligent dispatcher for Forge's 22 specialized agents. You describe a task, and the command analyzes its domain (architecture, backend, frontend, testing, devops, security, docs), complexity, and required skills, then recommends the best-fit agent with a match score and reasoning. It also suggests alternative agents in case you want a different approach.
Behind the scenes, the command uses keyword mapping to score each agent against the task description. Terms like "refactor" and "pattern" score high for the architect agents; "deploy" and "docker" score high for the devops agent; "vulnerability" and "audit" score high for the security agent. The scoring is transparent -- you see why a particular agent was chosen.
Without this command, you would need to memorize which of the 22 agents handles what, manually invoke the Task tool with the right agent type and prompt, and handle orchestrator task claiming yourself. /forge:agent-assign automates the matching, handles orchestrator integration (claiming tasks, locking files, recording knowledge), and confirms before launching.
Syntax & Options
/forge:agent-assign [task description] [--list] [--auto] [--agent <name>]
| Option | Description |
|---|---|
task description |
Natural language description of the task to assign |
--list |
Display all 22 available agents with their specialties and tools |
--auto |
Auto-assign based on task analysis without asking for confirmation (default behavior) |
--agent <name> |
Manually assign to a specific agent by name, bypassing the matching algorithm |
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.
- 3d ago First seen · 118 lines · 0 tokens per session scan A b286c9684ec7
agent-assign is a command published in the GitHub repository nxtg-ai/forge-plugin (5 stars, last pushed 13d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,265 tokens. 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.
Other commands, from other repositories
review-synthesize
Produce one evidence-based verdict, write the review report humans read, and publish it when the scope is a PR. You are read-only: never modify project files or commit; your only write outside the artifacts directory is the PR comment below. Read-only extends past the repository: a falsifying command creates its own…
triage
Confirm whether the work item still names real current work, choose the kind of reasoning owed next, and stop. Write the decisive evidence and handoff to $ARTIFACTSDIR/triage.md. You assess and route only: the repository must be exactly as you found it when you finish. No one watches the run; the report and your…
paul:help
Show available PAUL commands and usage guide.
verify
Grade work that already exists and decide whether it can merge. Runs the project's current unit, integration, and E2E suites plus security scanning and type checking, scores every dimension 0-10, and returns a merge verdict with a VERIFIED-vs-CLAIMED evidence manifest. Writes no test files and edits no source. Use…
paul:verify
Guide manual user acceptance testing of recently built features.
auto
Intent-classified router, the front door to OrchestKit and the DEFAULT entry point for any goal-shaped request. Classifies a plain-English goal and routes it to the right specialist skill. Routing is never overhead, so use it even when the target skill seems obvious; skip only when already executing inside another…