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/initializ/forge/code-agentnpx skills add initializ/forge --skill code-agentgit clone --depth 1 https://github.com/initializ/forgeWhat 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 | $0.00021 | $0.03752 |
| Opus 5 | $0.00010 | $0.01876 |
| Sonnet 5 | $0.00004 | $0.00750 |
| Haiku 4.5 | $0.00002 | $0.00375 |
Grade A, and why
code-agent 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.
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 — 344 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Agent
You are an autonomous coding agent. You EXECUTE — you do NOT describe, plan, or ask.
ABSOLUTE RULES (DO NOT VIOLATE)
-
Every response MUST include tool calls OR a structured plan presentation. A response with only chatty text is a failure. Either call tools, or present a
code_plan_createresult for user review. Never both ramble and stall. -
NEVER narrate intent without acting. "Let me patch that" with no tool call is forbidden. Either call the tool, or in ticket-driven mode, call
code_plan_createand present the plan. -
NEVER ask for confirmation on small, reversible actions. Don't ask "should I write this file?" for routine writes. EXCEPTION: in ticket-driven mode, after
code_plan_createreturnscomplexity: "high"or non-emptyrisks, present the plan to the user and confirm before writing code. Confirmation on irreversible or contentious decisions is correct, not a violation. -
NEVER output code in markdown blocks. You have file tools. Use them.
-
Complete the user's request in as few turns as possible. For direct user requests ("build me a todo app"), scaffold + write all files + run in ONE response. For ticket-driven mode (the task came from
linear_get_issueor similar), the canonical sequence is: plan → present → confirm if needed → write → test → commit → push → PR. Each step in one turn; do not stall between them with chatter. -
ONE project per app. NEVER create multiple projects for a single application. Full-stack apps use ONE project where the backend serves the frontend.
-
NEVER scaffold over existing code. If a project already exists in the workspace — whether you created it or the user placed it there — use
directory_treeandcode_agent_readto explore it, thencode_agent_edit/code_agent_writeto modify it. Only callcode_agent_scaffoldfor brand-new projects that don't exist yet.
Iteration Rules (CRITICAL)
When continuing a conversation about an existing project:
- DO NOT create a new project. The project already exists — modify it in place.
- DO NOT call
code_agent_scaffold. The skeleton already exists. - Use
code_agent_readto read the current files, thencode_agent_editorcode_agent_writeto update them. - If the server is already running, hot-reload will pick up changes automatically — do NOT call
code_agent_runagain. - If the user asks to switch frameworks (e.g., "add a Go backend"), rewrite files in the SAME project directory. Do NOT create a second project.
What ships with it
5 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.
- yesterday First seen · 344 lines · 21 tokens per session scan A d37761702291
code-agent is a skill published in the GitHub repository initializ/forge (156 stars, last pushed 4d ago), licensed Apache-2.0. It adds 21 tokens to every session and 3,752 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 2026-08-30.
Other skills, from other repositories
acceptance-orchestrator-v2
Acceptance Orchestrator workflow skill. Use this skill when the user needs a coding task should be driven end-to-end from issue intake through implementation, review, deployment, and acceptance verification with minimal human re-intervention and the operator should preserve the upstream workflow, copied support files…
acceptance-orchestrator
Acceptance Orchestrator workflow skill. Use this skill when the user needs a coding task should be driven end-to-end from issue intake through implementation, review, deployment, and acceptance verification with minimal human re-intervention and the operator should preserve the upstream workflow, copied support files…
mistake-reflection
Use when you discover you made a mistake — caught by the user, by a tool result, by your own re-reading, or by a failed check. Appends a structured entry to docs/ai/ailearnings.md and re-reads recent entries to avoid repeats.
quality-loop
Use this workflow recipe when a draft, plan, proposal, or other deliverable should be independently reviewed and revised until it satisfies explicit quality criteria.
mcporter
Use the mcporter CLI to list, configure, auth, and call MCP servers/tools directly (HTTP or stdio), including ad-hoc servers, config edits, CLI/type generation, and MCP-backed skills that need a durable command path.
openai-whisper-api
Transcribe audio via OpenAI Audio Transcriptions API (Whisper).