self-test

A test for a Bash safety guard. It sends dangerous command examples through the real guard as text and reports whether each would be blocked, require approval, or pass.

In plain words
What is it for?
Use it to check examples such as remote script execution, file deletion, database removal, cloud deletion, and Kubernetes deletion.
Why use it?
It lets you verify the protection works without actually running destructive commands.

Skill for Claude CodeCodex

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 skills/choiyounggi/groundwork/self-test
Any agent
npx skills add choiyounggi/groundwork --skill self-test
Clone the repo
git clone --depth 1 https://github.com/choiyounggi/groundwork

Made for: Claude Code, Codex.

Per session 79 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 261 The whole file, excluding the scripts and references it only reads on demand.
Security scan D 3 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 $0.00079 $0.00261
Opus 5 $0.00039 $0.00130
Sonnet 5 $0.00016 $0.00052
Haiku 4.5 $0.00008 $0.00026

Measured 2d ago against content hash bd99a501fe82, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade D, and why

self-test scanned grade D with 3 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 2d 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.

Unrestricted tool accessmediumExcessive agency

A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.

**not** execute any command.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

description: Prove the guardrails Bash guard is live — runs a simulation that feeds representative dangerous commands (curl|sh, rm -rf, DROP TABLE, kubectl delete, cloud deletes, …) through the real guard and shows the b

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

description: Prove the guardrails Bash guard is live — runs a simulation that feeds representative dangerous commands (curl|sh, rm -rf, DROP TABLE, kubectl delete, cloud deletes, …) through the real guard and shows the b
plugins/guardrails/skills/self-test/SKILL.md · 26 lines

What it actually says

guardrails: self-test

Run the bundled self-test to show the guard is active. It injects dangerous command strings into the guard as hook data and prints each decision — it does not execute any command.

Do this

  1. Run:
    bash "${CLAUDE_PLUGIN_ROOT}/scripts/self-test.sh"
    
  2. Show the user the output table verbatim.
  3. Summarize: block-tier commands were denied, ask-tier would prompt, harmless commands passed — and nothing was executed.

Hard rule

Never run any of the dangerous example commands yourself. The whole point is that they travel through the guard as data, never to a real shell. If the script exits non-zero, report which case mismatched — do not "fix" it by running commands.

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. 2d ago First seen · 26 lines · 79 tokens per session scan D bd99a501fe82

Subscribe to this mod's changes

self-test is a skill published in the GitHub repository choiyounggi/groundwork (3 stars, last pushed 2d ago), licensed MIT. It adds 79 tokens to every session and 261 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it D with 3 findings (unrestricted tool access, recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

dummy-dataset

Generate realistic dummy datasets for testing with customizable columns, constraints, and output formats (CSV, JSON, SQL, Python script). Use when creating test data, building mock datasets, or generating sample data for development and demos.

phuryn/pm-skills · 48 tokens

outcome-roadmap

Transform an output-focused roadmap into an outcome-focused one that communicates strategic intent. Rewrites initiatives as outcome statements reflecting user and business impacts. Use when shifting to outcome roadmaps, making a roadmap more strategic, or rewriting feature lists as outcomes.

phuryn/pm-skills · 53 tokens

retro

Facilitate a structured sprint retrospective — what went well, what didn't, and prioritized action items with owners and deadlines. Use when running a retrospective, reflecting on a sprint, creating action items from team feedback, or learning how to run effective retros.

phuryn/pm-skills · 52 tokens

release-notes

Generate user-facing release notes from tickets, PRDs, or changelogs. Creates clear, engaging summaries organized by category (new features, improvements, fixes). Use when writing release notes, creating changelogs, announcing product updates, or summarizing what shipped.

phuryn/pm-skills · 57 tokens

shipping-artifacts

The durable documentation set that makes an AI-built (vibe-coded) app reviewable before shipping. A small core every app needs — architecture, user/permission flows, permissions, variables/secrets, and a test-coverage map — plus conditional docs added only when they apply: emails, scheduled work, SEO, and embedded…

phuryn/pm-skills · 120 tokens

ideal-customer-profile

Identify the Ideal Customer Profile (ICP) from research data with demographics, behaviors, JTBD, and needs. Use when defining your ICP, analyzing PMF survey data, or understanding who your best customers are.

phuryn/pm-skills · 47 tokens