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 pan94u/forge --skill knowledge-generatorgit clone --depth 1 https://github.com/pan94u/forgeWrote 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/pan94u/forge/knowledge-generator)<a href="https://agentmods.dev/skills/pan94u/forge/knowledge-generator"><img src="https://agentmods.dev/badge/skills/pan94u/forge/knowledge-generator/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/pan94u/forge/knowledge-generator"><img src="https://agentmods.dev/badge/skills/pan94u/forge/knowledge-generator.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 | $0.00035 | $0.00579 |
| Opus 5.5 | $0.00014 | $0.00232 |
| Sonnet 5.5 | $0.00007 | $0.00116 |
| Haiku 4.5 | $0.00003 | $0.00058 |
Grade A, and why
knowledge-generator 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 1mo 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.
The source is not reproduced here
A licence we could not identify
The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.
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.
- 1mo ago First seen · 87 lines · 35 tokens per session scan A e80c033a194f
knowledge-generator is a skill published in the GitHub repository pan94u/forge (40 stars, last pushed 16d ago), with no licence file. It adds 35 tokens to every session and 579 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
knowledge_base
Manage the user's personal knowledge base — knowledge graph, documents, and wiki vault.
continuous-learning
Use when a mistake, correction, or surprise taught the workspace something that must stick — a retro or postmortem, the same agent error corrected twice, a resolved bug's root cause, scattered notes-to-self — and route that lesson to the durable surface that fires next time. NOT a forward choice with alternatives…
draft-edit
Produce minimal patch hunks against the supplied document snapshot for the requested edits.
document-export
One-shot export of a fixed Room document version to Feishu or Notion via the preinstalled lark-cli / OpenConnector channel, with explicit auth and confirmation gates.
draft-create
Draft a brand-new document from the instruction and material, returning the title and chunked body markdown.
document-cursor-completion
Complete a rich-text document at the cursor using the EverRoom FIM protocol. Use for editor cursor-completion requests.