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 skills add Riley-Coyote/mnemos --skill forgegit clone --depth 1 https://github.com/Riley-Coyote/mnemosWrote 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/riley-coyote/mnemos/forge)<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>- NVIDIA SkillSpector pass
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 | $0.00125 | $0.02120 |
| Opus 5 | $0.00063 | $0.01060 |
| Sonnet 5 | $0.00025 | $0.00424 |
| Haiku 4.5 | $0.00013 | $0.00212 |
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.
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 — 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]
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.
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.
- 8d ago First seen · 250 lines · 125 tokens per session scan A d0c75fc7448f
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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
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…
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…
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…