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 ychampion/cskill-agents --skill skill-scoped-permission-suggestionsgit clone --depth 1 https://github.com/ychampion/cskill-agentsWrote 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/ychampion/cskill-agents/skill-scoped-permission-suggestions)<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.
<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>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 | $0.00029 | $0.00419 |
| Opus 5 | $0.00015 | $0.00210 |
| Sonnet 5 | $0.00006 | $0.00084 |
| Haiku 4.5 | $0.00003 | $0.00042 |
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.
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.
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.
- 8d ago First seen · 28 lines · 29 tokens per session scan A 3e87a091744f
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.
Other skills, from other repositories
grape
Use Grape MCP for Codex context continuity in coding repositories. Use when a task needs repeated-turn context, omitted context restore, stale-context checks, invalidation checks, or safe continuity across branch and dirty-worktree changes.
review
Validate plans, execution, or PRs against wish criteria — returns SHIP / FIX-FIRST / BLOCKED with severity-tagged gaps.
work
Execute an approved wish plan — orchestrate subagents per task group with fix loops, validation, and review handoff.
brainstorm
Explore ambiguous or early-stage ideas interactively — tracks wish-readiness and crystallizes into a design for wish.
genie
Entry point for Genie operations — routes bug reports, questions, and operational commands, resumes existing lifecycle state, and orchestrates work that needs durable planning or coordination. Other ordinary requests bypass the lifecycle with a one-line notice unless the user asks for Genie.
wish
Convert an idea into a structured wish plan with scope, acceptance criteria, and execution groups for work.