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/sequenzia/agent-alchemy/oc-tool-devnpx skills add sequenzia/agent-alchemy --skill oc-tool-devgit clone --depth 1 https://github.com/sequenzia/agent-alchemyWhat 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 | $0.00075 | $0.02279 |
| Opus 5 | $0.00037 | $0.01140 |
| Sonnet 5 | $0.00015 | $0.00456 |
| Haiku 4.5 | $0.00007 | $0.00228 |
Grade A, and why
oc-tool-dev 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 — 272 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenCode Tool Dev
You are initiating the unified OpenCode tool development workflow. This process triages what the user needs, detects dependencies between artifacts, builds an execution plan, and delegates to the existing type-specific skills — reusing their interview flows and generation logic.
Critical Rules
AskUserQuestion is MANDATORY
IMPORTANT: You MUST use the AskUserQuestion tool for ALL questions to the user. Never ask questions through regular text output.
- Every triage question → AskUserQuestion
- Every dependency question → AskUserQuestion
- Confirmation questions → AskUserQuestion
Text output should only be used for summaries, explanations, and presenting information.
Skill Loader Pattern
This skill delegates to existing oc-create-* and oc-update-* skills. When executing a tool creation/update:
- Read the target skill's SKILL.md
- Follow its instructions as written
- Pre-fill known answers from triage to skip redundant questions
- The loaded skill is the single source of truth for its artifact type
Phase 1: Load References
Read the OpenCode platform overview for general context:
- Read
${CLAUDE_PLUGIN_ROOT}/references/platform-overview.md
Type-specific guides (skill-guide.md, agent-guide.md, command-guide.md) are loaded later by the delegated skill — do not load them here.
Phase 2: Triage Interview
Gather high-level requirements through 3 questions using AskUserQuestion.
Question 1 — Action:
- Header: "Action"
- Question: "What would you like to do?"
- Options:
- "Create new (Recommended)" — Create a new OpenCode tool from scratch
- "Update existing" — Update an existing tool to match current best practices
- multiSelect: false
Question 2 — Tool Type:
- Header: "Tool Type"
- Question: "What type of OpenCode tool?"
- Options:
- "Skill" — A SKILL.md workflow with phases, tools, and structured prompts
- "Agent" — A custom agent persona with model, permissions, and system prompt
- "Command" — A workflow shortcut with $VARIABLE placeholders and optional model override
- multiSelect: false
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 · 272 lines · 75 tokens per session scan A 365c04a0fba5
oc-tool-dev is a skill published in the GitHub repository sequenzia/agent-alchemy (43 stars, last pushed 3mo ago), licensed MIT. It adds 75 tokens to every session and 2,279 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
extension-creator
Create, scaffold, customize, validate, and locally test Qwen Code extensions. Use when the user wants a new Qwen Code extension, needs help choosing an extension template, wants to add QWEN.md context, commands, skills, agents, MCP servers, settings, hooks, channels, or LSP servers, or asks how to link and test an…
dispatching-parallel-agents
当面对 2 个以上可以独立进行、无共享状态或顺序依赖的任务时使用.
rulesync
Generates and syncs AI rule configuration files (.cursorrules, CLAUDE.md, copilot-instructions.md) across 20+ coding tools from a single source. Use when syncing AI rules, running rulesync commands, importing or generating rule files, or managing shared AI coding configurations.
autoprompt
Explicit-only useful-first orchestration. Invoke /autoprompt to turn a mission into one executable roadmap, build dependency-safe lanes, and verify the result with independent reviewers. Never infer invocation from ordinary requests. Never resume from leftover artifacts without an explicit resume instruction.
autoprompt
Explicit-only useful-first orchestration. Invoke /autoprompt to turn a mission into one executable roadmap, build dependency-safe lanes, and verify the result with independent reviewers. Never infer invocation from ordinary requests. Never resume from leftover artifacts without an explicit resume instruction.
autoprompt
Explicit-only useful-first orchestration. Invoke /autoprompt to turn a mission into one executable roadmap, build dependency-safe lanes, and verify the result with independent reviewers. Never infer invocation from ordinary requests. Never resume from leftover artifacts without an explicit resume instruction.