skill-scoped-permission-suggestions

skill-scoped-permission-suggestions is a skill for Claude Code, Codex from ychampion/cskill-agents. It costs 29 tokens per session (419 once invoked), scanned A, original, MIT.

A permission-scope helper that detects when a requested file belongs to one skill directory and suggests access limited to that directory.

In plain words
What is it for?
Use it when building filesystem permission prompts for project or global Claude skill files.
Why use it?
It avoids granting access to a whole skills folder when the task only needs one skill, while rejecting unsafe or ambiguous skill paths.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: reads .claude/ paths.

Good fit Use it when building filesystem permission prompts for project or global Claude skill files.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ychampion/cskill-agents/skill-scoped-permission-suggestions
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.

Any agent
npx skills add ychampion/cskill-agents --skill skill-scoped-permission-suggestions
Clone the repo
git clone --depth 1 https://github.com/ychampion/cskill-agents

Made for: Claude Code, Codex.

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-scoped-permission-suggestions

README.md
[![agentmods](https://agentmods.dev/badge/skills/ychampion/cskill-agents/skill-scoped-permission-suggestions/github.svg)](https://agentmods.dev/skills/ychampion/cskill-agents/skill-scoped-permission-suggestions)
Your own site
<a href="https://agentmods.dev/skills/ychampion/cskill-agents/skill-scoped-permission-suggestions"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/skill-scoped-permission-suggestions/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 skill-scoped-permission-suggestions

Your own site · 80×15
<a href="https://agentmods.dev/skills/ychampion/cskill-agents/skill-scoped-permission-suggestions"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/skill-scoped-permission-suggestions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 29 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 419 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.
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 $0.00029 $0.00419
Opus 5 $0.00015 $0.00210
Sonnet 5 $0.00006 $0.00084
Haiku 4.5 $0.00003 $0.00042

Measured 8d ago against content hash 3e87a091744f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

skill-scoped-permission-suggestions 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 8d 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/claude-code/skills/skill-scoped-permission-suggestions/SKILL.md · 28 lines

What it actually says

SKILL: Skill-Scoped Permission Suggestions

Domain: safety-worktrees
Trigger: Apply this when Claude is asking for filesystem permission that can be narrowed to a single skill directory. Source Pattern: Distilled from reviewed repo-safety, packaging, and worktree-management patterns.

Core Method

Leverage the skill path parser to detect when a target file resides inside .claude/skills/<skill-name> (project or global). Once matched, compute a gitignore-style prefix such as /.claude/skills/<skill-name>/** and offer that as the minimal scope for the permission prompt. This keeps the permission dialogue focused on the skill under edit and prevents giving blanket access to the entire .claude tree.

Key Rules

  • Normalize paths and compare lowercased versions so the detection works on both Windows and Unix filesystems.
  • Reject skill names that contain . or traversal segments before suggesting scopes to avoid leaking overlapping directories.
  • Always prefer /.claude/skills/<name>/** or ~/.claude/skills/<name>/** over /.claude/** whenever the file sits inside a skill.
  • When normalization finds no skill directory, fall back to the default wider scope instead of fabricating a useless pattern.

Example Application

When editing skills/my-skill/SKILL.md, call this method before showing the permission prompt so you can recommend granting /.claude/skills/my-skill/** instead of the entire .claude directory.

Anti-Patterns (What NOT to do)

  • Do not re-prompt with the same wide scope if the normalized path already resolves to a skill — that defeats the purpose of scoped access.
  • Don’t rely on raw casing or unnormalized separators; mismatched case would generate invalid patterns and quietly fall through.
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. 8d ago First seen · 28 lines · 29 tokens per session scan A 3e87a091744f

Subscribe to this mod's changes

skill-scoped-permission-suggestions is a skill published in the GitHub repository ychampion/cskill-agents (36 stars, last pushed 5mo ago), licensed MIT. It adds 29 tokens to every session and 419 once invoked, about $0.0001 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 2026-09-03.