permission-overlay-inheritance

permission-overlay-inheritance is a skill for Claude Code, Codex from ychampion/cskill-agents. It costs 24 tokens per session (399 once invoked), scanned A, original, MIT.

A permission-inheritance pattern for giving a child agent narrower rules while retaining the parent session's important grants.

In plain words
What is it for?
It helps safely configure permissions for subagents and nested workflows.
Why use it?
It avoids changing shared permissions or accidentally removing permissions supplied at the root level.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents.

Good fit It helps safely configure permissions for subagents and nested workflows.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ychampion/cskill-agents/permission-overlay-inheritance
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 permission-overlay-inheritance
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 permission-overlay-inheritance

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/ychampion/cskill-agents/permission-overlay-inheritance"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/permission-overlay-inheritance.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 24 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 399 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 $0.00024 $0.00399
Opus 5 $0.00012 $0.00199
Sonnet 5 $0.00005 $0.00080
Haiku 4.5 $0.00002 $0.00040

Measured 9d ago against content hash e8748db3fe17, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

permission-overlay-inheritance 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 9d 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/permission-overlay-inheritance/SKILL.md · 28 lines

What it actually says

SKILL: Permission Overlay Inheritance

Domain: permission-gating Trigger: Apply when a subagent or nested workflow needs a narrower permission contract but must still inherit the parent session's top-level grants. Source Pattern: Distilled from reviewed subagent orchestration, isolation, and lifecycle implementations.

Core Method

Start from the current app state, then derive a child-specific permission view by overlaying only the fields the child actually owns: permission mode, promptability flags, session-scoped allow rules, and effort level. Preserve parent bypass and SDK-level permissions so nested agents cannot accidentally weaken operator intent, and return the original state unchanged when no overlay is needed. This keeps permission inheritance explicit, composable, and side-effect-free.

Key Rules

  • Treat the parent permission context as the base contract; never mutate it in place when preparing a child view.
  • Allow child permission modes only when they do not override stronger parent modes like bypass permissions or accept edits.
  • Preserve root or CLI-supplied allow rules while replacing only the session-scoped rules the child explicitly owns.
  • Derive prompt-suppression flags from runtime reality, such as async execution or an explicit can show permission prompts override.

Example Application

If a background review agent should only use Read and Grep while the main session still has broader CLI-granted access, build its permission context as an overlay so the child narrows its own session rules without discarding the root-level contract.

Anti-Patterns (What NOT to do)

  • Do not copy the parent permission object and then mutate shared references; later agents will inherit unintended changes.
  • Do not wipe all inherited allow rules when a child provides allowed tools; preserve the parent layer that came from explicit operator input.
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. 9d ago First seen · 28 lines · 24 tokens per session scan A e8748db3fe17

Subscribe to this mod's changes

permission-overlay-inheritance is a skill published in the GitHub repository ychampion/cskill-agents (36 stars, last pushed 5mo ago), licensed MIT. It adds 24 tokens to every session and 399 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.