forgeos-skill-intake

forgeos-skill-intake is a skill for Claude Code from Nolane-x/forge-os. It costs 26 tokens per session (411 once invoked), scanned A, original, MIT.

A process for importing an external Agent Skill repository into ForgeOS as data without running its code. It checks the repository's contents, permissions, licensing, safety risks, duplicates, and usefulness before accepting it.

In plain words
What is it for?
Use it to collect an immutable source snapshot, find each skill file, preserve its text, scan for dangerous behavior, review licenses, detect duplicates, compare performance with no skill, and mark the result accepted, for review, quarantined, or duplicate.
Why use it?
External repositories may contain unsafe instructions, hidden dependencies, unclear licenses, or commands that access data or change systems. Inspecting them without execution lowers that risk.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the forgeos plugin — 196 skills, 1 command, 1 agent, 1 MCP server shipped together

Good fit Use it to collect an immutable source snapshot, find each skill file, preserve its text, scan for dangerous behavior, review licenses, detect duplicates, compare performance with no skill, and mark the result accepted, for review, quarantined, or duplicate.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/nolane-x/forge-os/forgeos-skill-intake
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 Nolane-x/forge-os --skill forgeos-skill-intake
Clone the repo
git clone --depth 1 https://github.com/Nolane-x/forge-os

Made for: Claude Code.

Or install forgeos, the plugin that ships this one along with the rest of its 196 skills, 1 command, 1 agent, 1 MCP server.

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 forgeos-skill-intake

README.md
[![agentmods](https://agentmods.dev/badge/skills/nolane-x/forge-os/forgeos-skill-intake.svg)](https://agentmods.dev/skills/nolane-x/forge-os/forgeos-skill-intake)
Your own site
<a href="https://agentmods.dev/skills/nolane-x/forge-os/forgeos-skill-intake"><img src="https://agentmods.dev/badge/skills/nolane-x/forge-os/forgeos-skill-intake.svg" alt="Measured on agentmods" height="20"></a>
Per session 26 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 411 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.
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 $0.00026 $0.00411
Opus 5 $0.00013 $0.00205
Sonnet 5 $0.00005 $0.00082
Haiku 4.5 $0.00003 $0.00041

Measured 8d ago against content hash bcc8342aacd8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

forgeos-skill-intake 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.

examples/skill-intake-kit-2026-07-28/forgeos-skill-intake/SKILL.md · 41 lines

What it actually says

ForgeOS Skill Intake

Use this procedure for every new external skill source.

Required inputs

  • Canonical repository URL.
  • Immutable snapshot reference, commit, or archive digest.
  • Source and per-skill license information.
  • Requested ForgeOS capability and permission envelope.

Procedure

  1. Download a repository snapshot as data. Never execute install hooks, scripts, binaries, or package lifecycle commands during discovery.
  2. Locate every SKILL.md case-insensitively and group only Markdown references that belong to the same skill directory.
  3. Preserve the original Markdown bytes. Put ForgeOS metadata in a separate FORGEOS_SKILL.json file.
  4. Scan for instruction override, credential access, data exfiltration, remote-shell piping, destructive filesystem operations, external writes, and hidden dependencies.
  5. Detect license family. Unknown, proprietary, or source-available terms must enter license review rather than automatic promotion.
  6. Compute normalized content hashes and mark duplicate skills instead of loading repeated copies.
  7. Compare the skill against a no-skill baseline on representative tasks.
  8. Assign one result: accepted, review, quarantine, or duplicate.

Boundaries

  • Intake approval does not grant runtime shell, network, credential, publishing, deletion, or deployment permission.
  • Registry popularity is not a security or quality signal.
  • A description is executable influence for retrieval and must be checked against the body and source repository.

Verification

Confirm that the output contains catalog.json, audit.csv, source-lock.json, and SUMMARY.md. Verify that quarantined Markdown was not copied unless an operator explicitly enabled that option.

Failure handling

On malformed archives, oversized Markdown, ambiguous provenance, or scanner failure, stop processing that source and record a source-level error. Do not silently downgrade the failure into acceptance.

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 · 41 lines · 26 tokens per session scan A bcc8342aacd8

Subscribe to this mod's changes

forgeos-skill-intake is a skill published in the GitHub repository Nolane-x/forge-os (10 stars, last pushed 1mo ago), licensed MIT. It adds 26 tokens to every session and 411 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.

Related

Other skills, from other repositories

ai-viral-team-script-writing

A guide for writing short-video scripts and shot lists, including dialogue, camera direction, character actions, mood, music, hooks, and endings. A shot list describes what happens in each camera shot.

aAAaqwq/AGI-Super-Team · 169 tokens

cinematic-video-gen

A prompt-writing guide for making AI-generated videos look more natural and expressive. It covers facial expressions, body movements, and keeping a character consistent between clips.

aAAaqwq/AGI-Super-Team · 87 tokens

clanker

Plan and review ERC20 deployment with the Clanker SDK. Use for token configuration, vesting, airdrops, rewards, metadata, and transaction preparation on supported EVM chains.

aAAaqwq/AGI-Super-Team · 40 tokens

content-typography

A Chinese-language typography and layout guide for content images such as social-media covers, article headers, and posters. It covers headline wording, line breaks, hierarchy, font weight, alignment, spacing, and platform fit.

aAAaqwq/AGI-Super-Team · 128 tokens

article-to-infographic

A planning tool that turns a long article or text into three to five visual-note plans. It extracts the main ideas, divides them into frames, and writes English prompts for styles such as mind maps, handwritten notes, architecture diagrams, and comparison grids.

aAAaqwq/AGI-Super-Team · 144 tokens

native-agent-swarms

Coordinate small teams of specialized Codex agents with bounded parallelism, explicit ownership, native messaging, and evidence-based synthesis. Use when two or more independent investigations, reviews, or implementation streams can run concurrently without sharing writable files, or when the user asks for swarm…

aAAaqwq/AGI-Super-Team · 70 tokens