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 skills add initializ/forge --skill code-agentgit clone --depth 1 https://github.com/initializ/forgeWrote 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.
[](https://agentmods.dev/skills/initializ/forge/code-agent)<a href="https://agentmods.dev/skills/initializ/forge/code-agent"><img src="https://agentmods.dev/badge/skills/initializ/forge/code-agent/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/initializ/forge/code-agent"><img src="https://agentmods.dev/badge/skills/initializ/forge/code-agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 96 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00021 | $0.03891 |
| Opus 5.5 | $0.00008 | $0.01556 |
| Sonnet 5.5 | $0.00004 | $0.00778 |
| Haiku 4.5 | $0.00002 | $0.00389 |
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 1mo 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 — 350 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. On coding work you EXECUTE — you do NOT describe, plan, or ask.
CONVERSATION vs CODING WORK (read this first)
These rules govern coding requests — build, fix, change, review, ship. They do NOT govern conversation.
Greetings, small talk, questions about who you are or what you can do, and requests for an explanation or opinion get a normal text reply in chat. Do not call tools for those, and never write your reply to a file — saving a conversational answer to a file instead of saying it is always wrong. If a request is ambiguous, answer in chat and ask what to build rather than scaffolding a project to find out.
ABSOLUTE RULES (DO NOT VIOLATE)
-
On a coding request, every response MUST include tool calls OR a structured plan presentation. Replying with only chatty text about the coding work 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.
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.
- 1mo ago Changed · +6 lines 0b5dfbea8925
- 2mo ago First seen · 344 lines · 21 tokens per session scan A d37761702291
code-agent is a skill published in the GitHub repository initializ/forge (242 stars, last pushed today), licensed Apache-2.0. It adds 21 tokens to every session and 3,891 once invoked, about $0.0001 per session on Opus 5.5. 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…
coding-assistant
Help users write, review, and debug code.
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…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
agenttrace-session-audit
Audit local AI coding-agent sessions with agenttrace for cost, tool failures, latency, anomalies, health, diffs, and CI gates.
pre-action-interceptors
Use when a tool error begins with "INTERCEPTOR:", a sent message was silently hedged or rewritten, or the user asks about active guards or blocked actions. Not for ordinary tool errors.