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 agentmods add skills/razaib-khan/forgeweave/code-buildernpx skills add Razaib-khan/ForgeWeave --skill code-buildergit clone --depth 1 https://github.com/Razaib-khan/ForgeWeaveWhat 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 | $0.00020 | $0.00577 |
| Opus 5 | $0.00010 | $0.00289 |
| Sonnet 5 | $0.00004 | $0.00115 |
| Haiku 4.5 | $0.00002 | $0.00058 |
Grade A, and why
Code Builder 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 2d 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Builder
Purpose
Take a structured plan and produce working, well-organized code. Makes architecture decisions (framework choice, folder structure, module boundaries), generates the code, and verifies it compiles or passes basic checks.
When to Use
- A
plannerskill has produced an execution plan - The user asks to "implement" or "build" a feature from requirements
- Scaffolding a new module, component, or service
- Translating architecture decisions into concrete code
When Not to Use
- The code change is a simple rename or refactor — use
refactor-engine - Only tests are needed — use
test-generator - The task is debugging an existing issue — use
debugger
Inputs
| Input | Type | Required | Description |
|---|---|---|---|
plan |
object | Yes | The execution plan from the planner skill |
existing_code |
string | No | Description of existing codebase structure |
standards |
array | No | Coding standards to follow (e.g., TypeScript strict, PEP 8) |
Expected Outputs
| Output | Description |
|---|---|
| New or modified files | Working code implementing the plan |
| Folder structure | Organized module layout |
| Architecture notes | Key decisions made during implementation |
Exact Workflow Steps
- Review the plan and understand the architecture
- Create folder structure matching project conventions
- Implement each module following existing patterns
- Add type annotations and documentation as code is written
- Verify the code compiles or passes syntax checks
- Run existing tests to confirm no regressions
Required Checks
- Code compiles without errors
- Existing tests still pass
- Code follows project conventions (naming, imports, formatting)
- New exports are properly typed
Failure Modes
| Failure Condition | Response |
|---|---|
| Code doesn't compile | Fix type errors and re-verify |
| Existing tests fail | Identify root cause and fix before continuing |
| Architecture decision contradicts plan | Flag to planner for resolution |
What ships with it
2 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.
- 2d ago First seen · 83 lines · 20 tokens per session scan A a6b05594e28d
Code Builder is a skill published in the GitHub repository Razaib-khan/ForgeWeave (1 stars, last pushed 2mo ago), licensed MIT. It adds 20 tokens to every session and 577 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.
Other skills, from other repositories
video-subtitles-and-audio-insert-workflow
Burn hard subtitles from UTF-8 SRT files using moviepy 2.x with CJK-capable system fonts; tune font size, placement, stroke, and encode settings (bitrate or CRF) to avoid oversized outputs. Documents ffprobe/ffmpeg workflows for inspection, encoding, and batch jobs; troubleshooting for fonts, bitrate, and pacing.…
Coding Agent
Guidance for when to delegate coding work to a specialized coding runtime or worker.
coding-conventions
Workforce coding conventions — read existing patterns, prefer narrow types, leave the surface area smaller than you found it.
roo-translation
Provides comprehensive guidelines for translating and localizing CoStrict extension strings. Use when tasks involve i18n, translation, localization, adding new languages, or updating existing translation files. This skill covers both core extension (src/i18n/locales/) and WebView UI (webview-ui/src/i18n/locales/)…
translate
다국어 번역 및 로컬라이제이션 (literal|natural|localize).
add-guided-tour
给本项目（@agent-spaces/web）的页面或组件添加 react-joyride 引导介绍。 Use whenever the user says 添加引导/添加介绍/加指引/onboarding/tour/新手引导/产品引导, or wants to highlight UI elements sequentially to explain a feature flow. 本 skill 已固化本项目的命名约定、i18n 结构、跨页触发机制和 flexlayout tab 锚点方案， 照做即可快速复用，无需重新摸索 API。.