AgentStack
SKILL verified Apache-2.0 Self-run

Askit Build Settings

skill-product-on-purpose-agent-skills-toolkit-askit-build-settings · by product-on-purpose

Creates and improves a plugin's settings and permissions per target and recommends least-privilege allowlists. Use when authoring settings, scoping permissions, wiring environment variables, or registering hooks in settings.

No reviews yet
0 installs
2 views
0.0% view→install

Install

$ agentstack add skill-product-on-purpose-agent-skills-toolkit-askit-build-settings

✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

Are you the author of Askit Build Settings? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

askit-build-settings

Purpose

Author and improve a plugin's settings and permissions, following the builder pattern ([../../docs/reference/builder-pattern.md](../../docs/reference/builder-pattern.md)). create scaffolds the settings per target (Claude Code settings.json - permissions, env, hook registration; Codex config.toml for the subset it supports); improve tightens an existing one. It also folds in permission advice: recommend the least-privilege allowlist a plugin needs, never broader (Standard sec 9). Recipe and the permission rubric are in [references/settings-recipe.md](references/settings-recipe.md).

When to use

When authoring settings, scoping permissions, wiring environment variables, or registering hooks in settings.

create mode

  1. Read what the plugin actually needs (which tools, which paths, which env, which hooks).
  2. Scaffold the settings per target: Claude Code settings.json (a permissions allow/deny set, env, and hooks registration); Codex config.toml for the subset it supports.
  3. Apply least privilege: the allowlist grants only what a component uses; secrets go through env indirection, never committed (sec 9).

improve mode

  1. Read the current settings and the components; remove any granted permission no component uses, and tighten an over-broad matcher.

permission advice

  1. For a given component or plugin, recommend the minimal allowlist (the narrowest tool set and path scope it needs) and flag any over-grant. This is the permission-advisor role, folded in as a mode rather than a separate skill.

Scope

Settings are partly cross-agent: Claude Code settings.json is the rich surface; Codex config.toml supports a subset. Least privilege and secret hygiene are Universal security rules (sec 9). Hook authoring itself is askit-build-hook; this skill wires a hook's registration entry. Status line registration is askit-build-statusline.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet — be the first.

Versions

  • v0.1.0 Imported from the upstream source.