tool-permission-planner

tool-permission-planner is a skill for Claude Code, Codex from 45ck/skill-harness. It costs 33 tokens per session (283 once invoked), scanned A, original, MIT.

A planning guide for deciding which tools an AI agent may use and what limits each tool needs.

In plain words
What is it for?
Use it to define read, write, command, network, approval, and audit boundaries for agent workflows, MCP servers, browser automation, and connectors.
Why use it?
It helps prevent an agent from seeing unnecessary data or making unwanted changes, especially when tools can affect files, accounts, or outside services.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to define read, write, command, network, approval, and audit boundaries for agent workflows, MCP servers, browser automation, and connectors.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/45ck/skill-harness/tool-permission-planner
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 45ck/skill-harness --skill tool-permission-planner
Clone the repo
git clone --depth 1 https://github.com/45ck/skill-harness

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 tool-permission-planner

README.md
[![agentmods](https://agentmods.dev/badge/skills/45ck/skill-harness/tool-permission-planner/github.svg)](https://agentmods.dev/skills/45ck/skill-harness/tool-permission-planner)
Your own site
<a href="https://agentmods.dev/skills/45ck/skill-harness/tool-permission-planner"><img src="https://agentmods.dev/badge/skills/45ck/skill-harness/tool-permission-planner/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 tool-permission-planner

Your own site · 80×15
<a href="https://agentmods.dev/skills/45ck/skill-harness/tool-permission-planner"><img src="https://agentmods.dev/badge/skills/45ck/skill-harness/tool-permission-planner.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 283 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 $0.00033 $0.00283
Opus 5 $0.00016 $0.00142
Sonnet 5 $0.00007 $0.00057
Haiku 4.5 $0.00003 $0.00028

Measured 9d ago against content hash 2582b7b3c8ef, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

tool-permission-planner 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.

packs/agent-operating-skills/skills/tool-permission-planner/SKILL.md · 36 lines

What it actually says

Tool Permission Planner

Use this skill when an agent needs tools beyond local read-only reasoning.

Process

  • Start from user task outcomes, not endpoint completeness.
  • List each tool, its side effects, and the data it can expose.
  • Choose read-only or dry-run modes first when they can prove the next step.
  • Define command, path, network, account, and write boundaries.
  • Name approval gates for destructive or externally visible actions.
  • Define audit evidence: logs, issue comments, manifests, screenshots, traces, or command output.

Permission Tiers

  • read: inspect files, issues, docs, metadata, screenshots
  • write-local: edit repo files or generated artifacts
  • execute-local: run tests, builds, formatters, or local validators
  • external-read: call APIs or remote systems without mutation
  • external-write: create, update, publish, deploy, merge, or notify
  • destructive: delete, revoke, reset, drop, overwrite, or irreversibly mutate

Output

Tool Surface

Minimum Required Tier

Boundaries

Approval Gates

Audit Evidence

Denied Capabilities

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 · 36 lines · 33 tokens per session scan A 2582b7b3c8ef

Subscribe to this mod's changes

tool-permission-planner is a skill published in the GitHub repository 45ck/skill-harness (15 stars, last pushed 2mo ago), licensed MIT. It adds 33 tokens to every session and 283 once invoked, about $0.0002 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 2026-08-30.