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 joaquimscosta/arkhe-claude-plugins --skill code-env-setupgit clone --depth 1 https://github.com/joaquimscosta/arkhe-claude-pluginsWrote 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/joaquimscosta/arkhe-claude-plugins/code-env-setup)<a href="https://agentmods.dev/skills/joaquimscosta/arkhe-claude-plugins/code-env-setup"><img src="https://agentmods.dev/badge/skills/joaquimscosta/arkhe-claude-plugins/code-env-setup/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/joaquimscosta/arkhe-claude-plugins/code-env-setup"><img src="https://agentmods.dev/badge/skills/joaquimscosta/arkhe-claude-plugins/code-env-setup.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 71 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 | $0.00090 | $0.00964 |
| Opus 5.5 | $0.00036 | $0.00386 |
| Sonnet 5.5 | $0.00018 | $0.00193 |
| Haiku 4.5 | $0.00009 | $0.00096 |
Grade A, and why
code-env-setup 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Code Setup Wizard
Interactive environment setup following the Claude Code Guide.
Pre-flight
Run the detection script to understand current state:
python3 ${CLAUDE_SKILL_DIR}/scripts/detect_setup.py
Two-Phase Workflow
Phase 1: Detect
-
Run the detector on the project root:
python3 ${CLAUDE_SKILL_DIR}/scripts/detect_setup.py <project-root> -
Fetch the guide via WebFetch:
https://raw.githubusercontent.com/joaquimscosta/arkhe-claude-plugins/main/docs/CLAUDE_CODE_GUIDE.mdIf WebFetch fails (network error, 404), warn the user and proceed using LLM knowledge only.
-
Cross-reference detection JSON against guide recommendations to identify what is missing or incomplete.
-
Detect MCP servers separately via Bash:
claude mcp list
Phase 2: Configure
- Present category selection using
AskUserQuestion(multiSelect: true). Show detection status for each category (configured / partially configured / not configured):
| # | Category | Guide Section | What It Configures |
|---|---|---|---|
| 1 | Global CLAUDE.md | Section 1 | ~/.claude/CLAUDE.md — security NEVER rules, account config |
| 2 | Project Scaffolding | Section 2 | .claude/ dirs, .env.example, .gitignore, CLAUDE.md |
| 3 | MCP Servers | Section 3 | Install recommended servers via claude mcp add |
| 4 | Hooks | Section 7 | ~/.claude/hooks/block-secrets.py, hooks in settings.json |
| 5 | Custom Agents | Section 10 | ~/.claude/agents/ starter agent files |
| 6 | Keybindings | Section 13 | ~/.claude/keybindings.json |
| 7 | Settings | Section 13 | Language, background tasks in settings.json |
If user passed a specific category as argument (e.g., /devtools:code-env-setup hooks), skip the selection and go directly to that category.
- Walk through each selected category with targeted
AskUserQuestioncalls. See WORKFLOW.md for per-category question flows.
What ships with it
4 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 First seen · 88 lines · 90 tokens per session scan A 1cf5c234994f
code-env-setup is a skill published in the GitHub repository joaquimscosta/arkhe-claude-plugins (21 stars, last pushed 9d ago), licensed MIT. It adds 90 tokens to every session and 964 once invoked, about $0.0004 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
git-workflow
Git branching, commits, and PR workflow following GitFlow conventions.
test-writer
Generate comprehensive tests including unit, integration, and property-based tests.
pm
Universal, project-agnostic PRODUCT MANAGER playbook — the scope-disciplined PM that plans a project, gates its launch, and says no. Five modes, one workflow each: prd (turn a spec or a user request into a build-ready PRD — objectives, in-scope, out-of-scope guards, an acceptance-criteria table mapping every success…
forge-behavior
Manage dotforge v3 behavior governance — view status, toggle behaviors, adjust strictness. Use when the user asks about active behaviors, wants to disable one for the current session, or adjust escalation thresholds.
earnings-watch
Quick post-earnings analysis for portfolio holdings. Beat/miss, key metrics, thesis impact, estimate revision. Triggers on "earnings update", "quarterly results", "Q1/Q2/Q3/Q4 results", "post-earnings".
quick
Fast path — skip the full workflow for small tasks under 3 files.