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 plan-mode-permission-gatinggit 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/plan-mode-permission-gating)<a href="https://agentmods.dev/skills/ychampion/cskill-agents/plan-mode-permission-gating"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/plan-mode-permission-gating/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/plan-mode-permission-gating"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/plan-mode-permission-gating.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 | $0.00026 | $0.00386 |
| Opus 5 | $0.00013 | $0.00193 |
| Sonnet 5 | $0.00005 | $0.00077 |
| Haiku 4.5 | $0.00003 | $0.00039 |
Grade A, and why
plan-mode-permission-gating 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 7d 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: Plan Mode Permission Gating
Domain: permission-gating Trigger: Invoke when the user wants to enter plan mode or a complex implementation requires additional permission scrutiny before introducing file edits. Source Pattern: Distilled from reviewed plan-mode entry and permission-transition implementations.
Core Method
Wrap plan-mode entry in an explicit permission transition. Validate that the request comes from the root session, switch the shared permission context into a planning state, and emit a standardized banner that reminds agents to explore before editing. Centralizing that transition prevents individual call sites from bypassing the plan-mode contract or drifting into edits before planning is complete.
Key Rules
- Treat plan-mode entry as a read-only permission change that cannot be invoked inside a child-agent context.
- Reconfigure the shared permission context through one centralized transition path so state sync and side effects stay consistent.
- Return a human-facing banner describing the plan-mode obligations, and let follow-up instructions adapt to the active plan-mode variant.
- Keep the tool’s UI payload minimal but explicit about the no-edit rule; reuse the same instructions for both regular and interview-enhanced plan mode.
Example Application
Use this skill when a CLI state machine detects a non-trivial refactor request: enter plan mode first, flip the session into a no-edit planning state, and require a reviewed plan before touching files.
Anti-Patterns (What NOT to do)
- Don’t let a code path change permissions directly without the standardized transition, or some agents will edge into edits without the plan-mode reminder.
- Don’t ignore agent forks — the gate belongs only to the root session, so refuse plan-mode tool calls when
context.agentIdis set.
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.
- 7d ago First seen · 29 lines · 26 tokens per session scan A 0c838f21c976
plan-mode-permission-gating is a skill published in the GitHub repository ychampion/cskill-agents (36 stars, last pushed 5mo ago), licensed MIT. It adds 26 tokens to every session and 386 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.