forge-plugin-creator

A set of instructions for creating and maintaining Forge plugins. Forge plugins are local extensions that can add tools, commands, and other integration points to Forge.

In plain words
What is it for?
Use it when creating, changing, checking, explaining, or testing Forge plugin code and configuration.
Why use it?
It helps keep plugin manifests, permissions, loading, and activation aligned with the available Forge APIs and safety rules.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/jslee124/forge/forge-plugin-creator
Any agent
npx skills add jslee124/forge --skill forge-plugin-creator
Clone the repo
git clone --depth 1 https://github.com/jslee124/forge

Made for: Claude Code, Codex.

Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 738 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00058 $0.00738
Opus 5 $0.00029 $0.00369
Sonnet 5 $0.00012 $0.00148
Haiku 4.5 $0.00006 $0.00074

Measured yesterday against content hash a925ac726a42, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

forge-plugin-creator 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 yesterday.

The scan reads SKILL.md. This mod also ships 2 executable files (templates/index.mjs, templates/plugin.test-template.ts), 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.

packages/resources/skills/forge-plugin-creator/SKILL.md · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Forge plugin creator

Use this workflow for Forge plugin work. This Skill is instruction text, not a plugin: it is never imported or executed and grants no filesystem, process, network, model, or approval capability. A generated plugin is trusted in-process JavaScript with the local privileges of Forge, so activation and trust must remain explicit.

Required inspection

Before generating or changing code:

  1. Inspect the active plugin.json schema in packages/plugin-api/src/schema.ts, the API types in packages/plugin-api/src/types.ts, and PLUGIN_API_VERSION when working in the Forge repository.
  2. Inspect the nearest maintained example under examples/plugins/ that uses the requested extension point.
  3. Outside the Forge repository, load the registered references/plugin-api.md resource supplied with this Skill. Treat its version as matching the installed CLI.
  4. Load a registered template only as a starting point. Adapt it to the task; do not copy capabilities or risks that are not needed.

Do not claim an API, capability, or hook exists without one of those sources.

Workflow

  1. Choose the scope: user plugins live at $FORGE_HOME/plugins/<name>/; project plugins live at <workspace>/.forge/plugins/<name>/ and require canonical project trust.
  2. Create a strict manifest and dependency-free .mjs entry when practical. The manifest name must equal its directory name.
  3. Declare only the capabilities actually used. A network-risk tool also requires network:access.
  4. Give every model-callable input a strict, bounded schema and label its real external effect: read, write, process, network, or model.
  5. Keep tool execution inside Forge's proposal, schema validation, policy, approval, execution, result, event, and trace path. Never perform the work from a prompt hook or observer to evade that path.
  6. Add focused tests that activate through the real plugin host when the Forge repository is available. Test invalid input and capability/trust boundaries, not only the success path.
  7. Document enablement or forge plugins trust; never silently edit trust state or imply that repository content is trusted merely because a Skill selected it.

Read the full file on GitHub · 71 lines

Files

What ships with it

4 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. yesterday First seen · 71 lines · 58 tokens per session scan A a925ac726a42

Subscribe to this mod's changes

forge-plugin-creator is a skill published in the GitHub repository jslee124/forge (2 stars, last pushed 2d ago), licensed MIT. It adds 58 tokens to every session and 738 once invoked, about $0.0003 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

systematic-debugging

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

obra/superpowers · 21 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

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

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens