ai-engineering: Skill for Claude Code

.agents/skills/ai-goal/SKILL.md

ai-goal is a skill for Claude Code from arcasilesgroup/ai-engineering. It costs 139 tokens per session (1,382 once invoked), scanned A, original, Apache-2.0.

A one-command workflow that takes a software goal through research, planning, implementation, review, testing, security checks, auditing, and delivery.

In plain words
What is it for?
Use it when you want one request carried through the repository’s defined development process and returned as a finished change to test.
Why use it?
It removes the need to coordinate each stage or approve steps during the run. It stops with a committed change, verification output, and a checklist for testing the result.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: installed under .agents/ (shared by several agents).

This is arcasilesgroup/ai-engineering's own configuration. It tells Claude Code how to work on ai-engineering itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything ai-engineering configures →

Reuse

Borrowing it

Nothing to install: this file belongs to arcasilesgroup/ai-engineering. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/arcasilesgroup/ai-engineering/main/.agents/skills/ai-goal/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/arcasilesgroup/ai-engineering

Made for: Claude Code.

Wrote 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.

agentmods badge for ai-goal

README.md
[![agentmods](https://agentmods.dev/badge/skills/arcasilesgroup/ai-engineering/ai-goal/github.svg)](https://agentmods.dev/skills/arcasilesgroup/ai-engineering/ai-goal)
Your own site
<a href="https://agentmods.dev/skills/arcasilesgroup/ai-engineering/ai-goal"><img src="https://agentmods.dev/badge/skills/arcasilesgroup/ai-engineering/ai-goal/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.

agentmods 80×15 button for ai-goal

Your own site · 80×15
<a href="https://agentmods.dev/skills/arcasilesgroup/ai-engineering/ai-goal"><img src="https://agentmods.dev/badge/skills/arcasilesgroup/ai-engineering/ai-goal.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 139 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,382 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 5.1 $0.00139 $0.01382
Opus 5 $0.00069 $0.00691
Sonnet 5 $0.00028 $0.00276
Haiku 4.5 $0.00014 $0.00138

Measured 9d ago against content hash dbeb4c3220f0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

ai-goal 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 9d 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.

.agents/skills/ai-goal/SKILL.md · 106 lines

How it starts

The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.

One run, no mid-run stop

/ai-goal <goal> is the person saying "this one runs without me". The whole cycle runs in one pass and the person comes back only when there is a finished thing to test. The invocation is the standing approval; you never ask again, and you never claim an approval you did not earn.

What it produces

The finished thing handed to the person: the change committed at HEAD, the ai-eng audit verify gate output shown in full, and the acceptance checklist the person runs against the real artifact.

The order

Read policy/skill-sequence.toml and follow it; if that file is absent, refuse to continue — the order is data, not prose. Load each stage's own skill and follow it: /ai-research, /ai-spec, /ai-challenge, /ai-council, /ai-build, /ai-review, /ai-verify, /ai-security, the audit verb, then /ai-ship.

Tiers, per the repository's pin

Each stage runs on the tier the repository's [models] section configures — never a model name coded into this skill, and never a provider the repository did not choose. Ask the tier the stage deserves, matching model_router's own mapping: research and spec run on the low tier, security, review, plan and audit on the top tier, and build, verify, ship (and everything the pin leaves untiered) on medium, falling back to default_tier when a tier is not configured. The command event records which model the pin says each verb routes to (tier_model) and what the surface actually ran (model); the two are different facts and the run never conflates them.

Tools are whatever the client has

The cycle uses only the tools present on this machine: the local floor (the repository, the IDE and the assigned surface, the ai-eng harness, the model available) is always on, and a web provider or NotebookLM is used only when the client configured it. An absent tool degrades the stage that would use it — the research stage names degraded-tool: <name> and carries on with the local floor. Nothing in this skill depends on a tool the client does not have.

Read the full file on GitHub · 106 lines

Files

What ships with it

1 file 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. 9d ago First seen · 106 lines · 139 tokens per session scan A dbeb4c3220f0

Subscribe to this mod's changes

ai-goal is a skill published in the GitHub repository arcasilesgroup/ai-engineering (54 stars, last pushed yesterday), licensed Apache-2.0. It adds 139 tokens to every session and 1,382 once invoked, about $0.0007 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.