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 GregoryHo/arcforge --skill usinggit clone --depth 1 https://github.com/GregoryHo/arcforgeWrote 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/gregoryho/arcforge/using)<a href="https://agentmods.dev/skills/gregoryho/arcforge/using"><img src="https://agentmods.dev/badge/skills/gregoryho/arcforge/using/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/gregoryho/arcforge/using"><img src="https://agentmods.dev/badge/skills/gregoryho/arcforge/using.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00045 | $0.01078 |
| Opus 5.5 | $0.00018 | $0.00431 |
| Sonnet 5.5 | $0.00009 | $0.00216 |
| Haiku 4.5 | $0.00005 | $0.00108 |
Grade A, and why
using 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 today.
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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Using arcforge
Pick the smallest workflow that fits. This skill is an index, not a gate: find the row that matches your situation, invoke that skill, and stop reading here. If nothing matches, no arcforge skill applies — just do the work.
Skill Map
| Skill | Use when |
|---|---|
/writing-skills |
you are authoring or revising an arcforge skill (user-invoked) |
/brainstorming |
a request is underspecified, several designs are plausible, or the user is thinking out loud rather than asking for code |
/executing |
work needs more than one step, a task list is waiting to be run, or you are choosing between attended and unattended execution |
/speccing |
the user asks to start keeping product intent under product/; or a project already keeps it there and one of these applies — a wish needs capturing, a version needs its spec before it is built, a recorded decision is being reversed, or a shipped version needs its roadmap and spec flipped |
/tdd |
you are about to write implementation code, fix a bug, or found code with no test |
/debugging |
a test fails, a bug is reported, behavior surprises you, a build breaks, or a fix you tried did not hold |
/code-review |
a change is ready to hand off — the diff needs review before it merges, or review feedback just came back |
/dispatching |
work could run in parallel — splitting it across agents, giving each an isolated worktree, briefing them, or accepting what comes back |
/finishing |
implementation is done and the branch or worktree needs merging, a PR, keeping, or discarding |
/sessions |
context is about to be lost — work is stopping mid-task and the next session or another person has to pick it up, you are starting from an earlier handover or a named session archive, the user wants the session saved under a name, or a long session is filling up and you are deciding whether to compact |
/learning |
you are capturing a session diary, mining diaries for patterns, or reviewing what the opt-in learning subsystem wants to activate (user-invoked) |
/looping |
you are handing a task list to an unattended loop that will keep working after you walk away (user-invoked) |
/evaluating |
a claim about agent behavior needs evidence — you are designing or auditing an eval scenario, or reading a verdict out of eval numbers |
/maintaining-obsidian |
something should be filed into the user's Obsidian vault, a question should be answered from it, or it needs auditing or bootstrapping |
/diagramming-obsidian |
the user wants something shown visually — an architecture, a flow, a mind map — as an Excalidraw diagram in their vault |
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.
- today First seen · 59 lines · 45 tokens per session scan A e5fd4c61cc6f
using is a skill published in the GitHub repository GregoryHo/arcforge (8 stars, last pushed 12d ago), licensed MIT. It adds 45 tokens to every session and 1,078 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-11-07.
using compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| usingGregoryHo/arcforge | Skill | 8 | 12d ago | MIT | A | 45 | Claude Code, Codex |
| orbit-notionnexu-io/open-design | Skill | 106k | yesterday | Apache-2.0 | A | 117 | Claude Code, Codex |
| agentmailpaperclipai/paperclip | Skill | 111k | yesterday | MIT | A | 30 | Claude Code, Codex |
| Cortexdanielmiessler/LifeOS | Skill | 20k | yesterday | MIT | A | 184 | Claude Code |
| rowboat-spacesrowboatlabs/rowboat | Skill | 18k | yesterday | Apache-2.0 | A | 60 | Claude Code, Codex |
| feishuHmbown/CodeWhale | Skill | 41k | 5d ago | MIT | A | 33 | Claude Code, Codex |
| pinchtab-mcppinchtab/pinchtab | Skill | 11k | 10d ago | MIT | A | 52 | Claude Code, Codex |