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 skills/razaib-khan/forgeweave/agent-spawnernpx skills add Razaib-khan/ForgeWeave --skill agent-spawnergit clone --depth 1 https://github.com/Razaib-khan/ForgeWeaveWrote 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/razaib-khan/forgeweave/agent-spawner)<a href="https://agentmods.dev/skills/razaib-khan/forgeweave/agent-spawner"><img src="https://agentmods.dev/badge/skills/razaib-khan/forgeweave/agent-spawner.svg" alt="Measured on agentmods" 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 | $0.00020 | $0.00602 |
| Opus 5 | $0.00010 | $0.00301 |
| Sonnet 5 | $0.00004 | $0.00120 |
| Haiku 4.5 | $0.00002 | $0.00060 |
Grade A, and why
Agent Spawner 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 4d 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Spawner
Purpose
Dynamically create and configure sub-agents for specific tasks. Each spawned agent gets a defined role, constraints, tool permissions, and a task-specific prompt. Enables the multi-agent patterns used in deep-research and workflow-orchestrator.
When to Use
- A multi-agent pipeline needs to be executed (e.g., deep-research)
- A task requires a specialized agent with specific permissions
- Parallel execution of independent subtasks is needed
- An agent needs to be sandboxed with restricted capabilities
When Not to Use
- The task is simple enough for a single agent
- The user explicitly asked for a single-agent approach
- The overhead of spawning a sub-agent exceeds the complexity of the task
Inputs
| Input | Type | Required | Description |
|---|---|---|---|
task |
string | Yes | What the sub-agent should do |
role |
string | Yes | The sub-agent's role (e.g., "researcher", "validator") |
constraints |
array | No | Rules the sub-agent must follow |
permissions |
object | No | Tool permissions for the sub-agent |
Expected Outputs
| Output | Description |
|---|---|
| Spawned agent | A configured sub-agent ready to execute |
| Agent manifest | The agent's instructions and constraints |
Exact Workflow Steps
- Define the agent's role based on the task requirements
- Set constraints: what the agent MUST and MUST NOT do
- Set permissions: which tools the agent can use
- Write the agent's instructions prompt
- Spawn the agent using the TUI's sub-agent mechanism
- Monitor execution for constraint violations
Required Checks
- Agent has a clearly defined role
- Constraints are explicit and enforceable
- Permissions match the task requirements
- Agent instructions are self-contained
Failure Modes
| Failure Condition | Response |
|---|---|
| Permission mismatch | Adjust permissions to match the task |
| Agent goes out of scope | Enforce constraints and restart |
| Sub-agent mechanism unavailable | Execute the task directly with a prompt template |
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 4d ago First seen · 84 lines · 20 tokens per session scan A e86c85de1742
Agent Spawner is a skill published in the GitHub repository Razaib-khan/ForgeWeave (1 stars, last pushed 2mo ago), licensed MIT. It adds 20 tokens to every session and 602 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.
Other skills, from other repositories
tmux
Remote-control tmux sessions for interactive CLIs by sending keystrokes and scraping pane output.
summarize
Summarize or extract text/transcripts from URLs, podcasts, and local files (great fallback for “transcribe this YouTube/video”).
foundry-config-setup
Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.
complete-partial-pr
Evaluate and complete an issue or PR where the submitted patch fixes only a narrow symptom of the reported pain point. Use when a contribution may miss adjacent integration surfaces, provider/spec semantics, roundtrip behavior, tests, docs, or historical maintainer decisions.
hive.chart-creation-foundations
Required reading whenever any chart tool is available. Teaches the one-tool embedding contract (call chartrender → live chart appears in chat AND a downloadable PNG lands in the queen session dir), the ECharts (data viz) vs Mermaid (structural diagrams) decision, the BI/financial-grade aesthetic baseline (no…
embedding-strategies
Select and optimize embedding models for semantic search and RAG applications. Use when choosing embedding models, implementing chunking strategies, or optimizing embedding quality for specific domains.