skill-clare-env-setup

skill-clare-env-setup is a cursor rule for Cursor from jketreno/clare. It costs 9 tokens per session (625 once invoked), scanned A, original, MIT.

A repository-scanning setup helper for CLARE projects. It identifies languages, configuration files, verification requirements, and likely build or test areas.

In plain words
What is it for?
It helps generate environment reports, recommend VS Code extensions, produce machine-readable scan results, and optionally create an isolated verification Dockerfile.
Why use it?
It shows contributors what their environment needs and where verification coverage may still be missing.

Cursor rule for Cursor

Install

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.

agentmods
npx agentmods add rules/jketreno/clare/skill-clare-env-setup
Clone the repo
git clone --depth 1 https://github.com/jketreno/clare

Made for: Cursor.

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 skill-clare-env-setup

README.md
[![agentmods](https://agentmods.dev/badge/rules/jketreno/clare/skill-clare-env-setup.svg)](https://agentmods.dev/rules/jketreno/clare/skill-clare-env-setup)
Your own site
<a href="https://agentmods.dev/rules/jketreno/clare/skill-clare-env-setup"><img src="https://agentmods.dev/badge/rules/jketreno/clare/skill-clare-env-setup.svg" alt="Measured on agentmods" height="20"></a>
Per session 9 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 625 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00009 $0.00625
Opus 5 $0.00005 $0.00313
Sonnet 5 $0.00002 $0.00125
Haiku 4.5 $0.00001 $0.00063

Measured 5d ago against content hash 1ddbf6858890, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

skill-clare-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 5d 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.

.cursor/rules/skill-clare-env-setup.mdc · 55 lines

What it actually says

CLARE Skill: clare-env-setup

description: Detect project file types, recommend tools and VS Code extensions, and optionally generate Dockerfile.clare for reproducible verification runs.


This skill provides an env-scan helper that inspects a repository, reports which languages and common config files are present, extracts tooling requirements from clare/verify-ci.sh and clare/verify-local.sh, recommends VS Code extensions, and identifies likely deployment/build/test surfaces that still need CLARE coverage.

Purpose

  • Help contributors quickly configure their environment for CLARE verification.
  • Provide a small Dockerfile.clare to run verification in an isolated container.

Usage

Installing this skill also installs the scanner into your project at clare/scripts/clare-env-scan.sh. Run it from the project root:

  • Run the scanner (human-readable report):

    bash clare/scripts/clare-env-scan.sh --report

  • Machine-readable JSON output:

    bash clare/scripts/clare-env-scan.sh --json > /tmp/clare-scan.json

  • Attempt to update .vscode/extensions.json in the repository (use with care):

    bash clare/scripts/clare-env-scan.sh --apply-extensions --vscode-dir .vscode

Notes

  • The scanner is intentionally conservative and will only auto-apply VS Code recommendations when explicitly requested.
  • The CLARE source repo also ships a Dockerfile.clare (under install/): a suggested, minimal image to run ./clare/verify-ci.sh --fast without polluting the host. Copy it into your project and edit it to add or remove language runtimes as needed.

Dockerfile details

  • The CLARE source repo's install/Dockerfile.clare installs the Go toolchain from the official tarball by default (build-arg GO_VERSION=1.22.9). This enables language checks that require go and binaries installed via go install (for example shfmt) to be available inside the container. To override the Go version or skip installation, use --build-arg GO_VERSION=... or an empty value to skip.

Installer usage

  • The installer supports non-interactive skill installation with the --install-skill flag. You can pass a quoted list of numeric indices (as shown during the setup prompt) or all. Example:
./scripts/clare-installer.sh --target /path/to/project --install-skill "1"
./scripts/clare-installer.sh --target /path/to/project --install-skill "all"

Outputs

  • Plain text report (default --report).
  • JSON (--json) with fileCounts, configsFound, verifyTools, recommendedExtensions, detectedSurfaces, verifiedSurfaces, coverageGaps, and agentPrompts sections.

See install/clare/README.md for additional details and examples.

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. 5d ago First seen · 55 lines · 9 tokens per session scan A 1ddbf6858890

Subscribe to this mod's changes

skill-clare-env-setup is a cursor rule published in the GitHub repository jketreno/clare (5 stars, last pushed 1mo ago), licensed MIT. It adds 9 tokens to every session and 625 once invoked, about $0.0000 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 2026-08-31.