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 permission-overlay-inheritancegit 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/permission-overlay-inheritance)<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.
<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>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 | $0.00024 | $0.00399 |
| Opus 5.5 | $0.00010 | $0.00160 |
| Sonnet 5.5 | $0.00005 | $0.00080 |
| Haiku 4.5 | $0.00002 | $0.00040 |
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 1mo 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: 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.
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.
- 1mo ago First seen · 28 lines · 24 tokens per session scan A e8748db3fe17
permission-overlay-inheritance is a skill published in the GitHub repository ychampion/cskill-agents (36 stars, last pushed 6mo ago), licensed MIT. It adds 24 tokens to every session and 399 once invoked, about $0.0001 per session on Opus 5.5. 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.
gh
GitHub CLI skill for interacting with GitHub via the gh command line tool. Use when Bub needs to (1) Create, view, or manage GitHub repositories, (2) Work with issues and pull requests, (3) Create and manage releases, (4) Run and monitor GitHub Actions workflows, (5) Create and manage gists, (6) Install and manage…
brain-ingest
The process for digesting a conversation, document, or research result, classifying it, and writing it down as brain content (a root-page update or a new/updated page) through the brain CLI.
wish
Deliver one decided task end to end — admit it, work it in one worktree, gate, independent review, bounded repair, a merge-ready PR — or plan a multi-group wish when it is bigger than one task.
gate-control
Canonical VideoStudio review authorization and state-transition policy. Use after any Gate B/C/Preview/D decision, post-gate revision, resumed approval, or exhausted visual-QA result across COMPOSE/AUTO/GENERATE/EDIT; maps explicit user authority and durable artifact state to one next action with ovs gate transition.…
report
Investigate a failure to its root cause with grounded evidence, hand the diagnosis to fix, and create a GitHub issue only when asked.