forge

forge is a skill for Claude Code, Codex from Riley-Coyote/mnemos. It costs 125 tokens per session (2,120 once invoked), scanned A, original, MIT.

A tool for creating OpenClaw agents or sending coding agents to visible terminal sessions. OpenClaw is an agent platform in which separate agents can be configured and run.

In plain words
What is it for?
Use it to create an agent, clone or configure one, dispatch coding work, or send several agents to separate tasks in parallel.
Why use it?
It helps divide work between persistent agents or delegate coding tasks to another active terminal session.

Skill for Claude CodeCodex

Which agent this was written for is unclear — built for openclaw. Also seen: mentions Claude Code; mentions AGENTS.md; mentions Codex.

Good fit Use it to create an agent, clone or configure one, dispatch coding work, or send several agents to separate tasks in parallel.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/riley-coyote/mnemos/forge
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.

Any agent
npx skills add Riley-Coyote/mnemos --skill forge
Clone the repo
git clone --depth 1 https://github.com/Riley-Coyote/mnemos

Made for: Claude Code, Codex.

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 forge

README.md
[![agentmods](https://agentmods.dev/badge/skills/riley-coyote/mnemos/forge.svg)](https://agentmods.dev/skills/riley-coyote/mnemos/forge)
Your own site
<a href="https://agentmods.dev/skills/riley-coyote/mnemos/forge"><img src="https://agentmods.dev/badge/skills/riley-coyote/mnemos/forge.svg" alt="Measured on agentmods" height="20"></a>
Per session 125 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,120 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00125 $0.02120
Opus 5 $0.00063 $0.01060
Sonnet 5 $0.00025 $0.00424
Haiku 4.5 $0.00013 $0.00212

Measured 8d ago against content hash d0c75fc7448f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

forge 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 8d ago.

The scan reads SKILL.md. This mod also ships 3 executable files (scripts/forge-detect.sh, scripts/forge-pane.sh, scripts/forge.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

forge/SKILL.md · 250 lines

How it starts

The opening of the file, as written. The whole thing — 250 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Forge

Two capabilities in one skill: Create new OpenClaw agents, or Dispatch coding agents to visible terminal panes.


Decision Tree

When the user's request comes in, determine which mode:

Is the user asking to create/spin up a new persistent agent?
  YES → CREATE mode (forge.py)
  NO  →
    Is the user asking to build/code/fix something that should be delegated?
    Or explicitly saying "dispatch", "send an agent", "have an agent work on"?
      YES → DISPATCH mode (forge-pane.sh)
      NO  → Handle normally (not a Forge task)

Signals for CREATE:

  • "create agent", "new agent", "spin up agent", "forge agent", "bootstrap agent"
  • "clone agent", "make an agent like X"
  • Discussing agent names, models, personalities, Telegram bindings

Signals for DISPATCH:

  • "build this", "have an agent work on this", "dispatch", "send an agent to"
  • Any coding task the main agent should delegate rather than do inline
  • "use codex/claude for this" (agent override)
  • "do these in parallel" (multi-dispatch)

CREATE — New OpenClaw Agent

Creates a fully operational OpenClaw agent with workspace, identity files, config registration, auth profiles, and model routing.

Parameters

Gather these from the user (ask only what's missing):

Parameter Required Default Notes
name yes Lowercase, becomes agent ID
primary_model yes Format: provider/model (e.g., openai/gpt-5.4)
fallback_models no [] Comma-separated fallback chain
personality no minimal template Path to custom SOUL.md
telegram_bot_token no skip binding For Telegram integration
clone_from no fresh agent Clone identity from existing workspace

Execution

python3 scripts/forge.py \
  --name <agent-name> \
  --model <primary-model> \
  [--fallbacks <model1>,<model2>] \
  [--clone-from <existing-workspace-path>] \
  [--personality <path-to-soul.md>] \
  [--telegram-token <bot-token>] \
  [--openrouter-key <key>] \
  [--force]

Read the full file on GitHub · 250 lines

Files

What ships with it

5 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.

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. 8d ago First seen · 250 lines · 125 tokens per session scan A d0c75fc7448f

Subscribe to this mod's changes

forge is a skill published in the GitHub repository Riley-Coyote/mnemos (49 stars, last pushed 1mo ago), licensed MIT. It adds 125 tokens to every session and 2,120 once invoked, about $0.0006 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens