agentmods.dev

approval-first-planner

approval-first-planner is a skill for Claude Code, Codex from blackzhanzhan/Cyber-Ming-Protocol. It costs 64 tokens per session (2,270 once invoked), scanned A, original, MIT.

A planning skill for implementation work that changes code, files, pages, or project structure. It inspects the project and produces an approval-first contract without editing anything.

In plain words
What is it for?
Use it to plan fixes, refactors, and other file-changing tasks with atomic work slices, test cases, target files, and a commit plan.
Why use it?
It makes the intended changes, boundaries, tests, and acceptance criteria explicit before work begins. This gives someone a clear point to approve or reject the proposed execution.

Skill for Claude CodeCodex

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

not rated 56repo 4mo ago A scan 64 tokens original MIT

Good fit Use it to plan fixes, refactors, and other file-changing tasks with atomic work slices, test cases, target files, and a commit plan.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/blackzhanzhan/cyber-ming-protocol/approval-first-planner
View source ↗ blackzhanzhan/Cyber-Ming-Protocol
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 blackzhanzhan/Cyber-Ming-Protocol --skill approval-first-planner
Clone the repo
git clone --depth 1 https://github.com/blackzhanzhan/Cyber-Ming-Protocol

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 approval-first-planner

README.md
[![agentmods](https://agentmods.dev/badge/skills/blackzhanzhan/cyber-ming-protocol/approval-first-planner/github.svg)](https://agentmods.dev/skills/blackzhanzhan/cyber-ming-protocol/approval-first-planner)
Your own site
<a href="https://agentmods.dev/skills/blackzhanzhan/cyber-ming-protocol/approval-first-planner"><img src="https://agentmods.dev/badge/skills/blackzhanzhan/cyber-ming-protocol/approval-first-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 approval-first-planner

Your own site · 80×15
<a href="https://agentmods.dev/skills/blackzhanzhan/cyber-ming-protocol/approval-first-planner"><img src="https://agentmods.dev/badge/skills/blackzhanzhan/cyber-ming-protocol/approval-first-planner.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 64 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,270 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 $0.00064 $0.02270
Opus 5 $0.00032 $0.01135
Sonnet 5 $0.00013 $0.00454
Haiku 4.5 $0.00006 $0.00227

Measured 10d ago against content hash 12400f8f382f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

approval-first-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 10d 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.

skill/approval-first-planner/SKILL.md · 184 lines

How it starts

The opening of the file, as written. The whole thing — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Approval-First Planner

Prerequisite: read and obey the repository parent policy at skill/global_rules/SKILL.md first.

Use When

  • The user asks to implement, fix, refactor, modify, or take over a task that will change files.
  • The user wants a plan before edits.
  • The request may be phrased in plain register, imperial register, Chinese, or English.

Goal

  • Convert a task request into an executable, auditable, approval-first contract.
  • Expose boundaries before any edits begin.
  • Make the boundary model explicit enough that execution can continue continuously until a real red line is crossed.
  • Keep the contract attached to a visible campaign tree rather than letting local replans silently replace the mainline.

Output Contract

Your response must stop before editing and must include:

  1. A short stop-before-edit notice.
  2. A Markdown table titled Minimal Atomic Execution Contract for English users or 最小改动原子执行合同 for Chinese users.
  3. A YAML block titled Boundary Conditions And Test-Case Key Map for English users or 边界条件与测试用例键值对 for Chinese users.
  4. An explicit approval gate.

Required Table Shape

Each atomic slice must expose at least these fields:

  • Slice ID
  • Objective
  • Allowed Files
  • Do Not Touch
  • Red Line
  • Green Tests
  • Acceptance Ladder
  • Commit Action
  • Commit Unit
  • Commit Message
  • Target Artifacts
  • Affected Architecture Nodes
  • Architecture Delta
  • Amendment Required
  • Affected Data Entities
  • Data Model Delta
  • ER Amendment Required
  • Migration Required
  • Backfill Required

Required YAML Shape

The acceptance YAML block must not collapse governance red lines and white-box test chains into one blur.

It must distinguish:

  • governance-layer red_line
  • white-box assertions
  • white-box red_test
  • white-box green_test
  • same_case_requirement
  • physical_evidence
  • affected_architecture_nodes
  • unchanged_architecture_nodes
  • architecture_delta
  • requires_architecture_amendment
  • affected_data_entities
  • unchanged_data_entities
  • data_model_delta
  • requires_er_amendment
  • migration_required
  • backfill_required

Read the full file on GitHub · 184 lines

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. 10d ago First seen · 184 lines · 64 tokens per session scan A 12400f8f382f

Subscribe to this mod's changes

approval-first-planner is a skill published in the GitHub repository blackzhanzhan/Cyber-Ming-Protocol (56 stars, last pushed 4mo ago), licensed MIT. It adds 64 tokens to every session and 2,270 once invoked, about $0.0003 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.

Planningagent-governanceagent-workflowai-agentai-codingdeveloper-tools
Related

Other skills, from other repositories

loop-execution

Use when executing an existing HOTL workflow file — reads steps, loops until success criteria met, auto-approves low-risk gates, pauses at high-risk gates.

yimwoo/hotl-plugin · 37 tokens

executing-plans

Use when executing an implementation plan linearly with explicit human checkpoints between batches of tasks.

yimwoo/hotl-plugin · 22 tokens

brainstorming

Use before any feature work — explores intent, requirements, and design. Produces HOTL contracts (intent, verification, governance) before implementation.

yimwoo/hotl-plugin · 33 tokens

pr-reviewing

Review a PR across multiple dimensions — description, code changes, code scan, unit tests — using parallel subagents. Supports GitHub, GitLab, and enterprise platforms.

yimwoo/hotl-plugin · 38 tokens

subagent-execution

Delegated step runner over the HOTL execution state machine — delegates eligible steps to fresh subagents while the controller keeps governance, verification, and stop conditions.

yimwoo/hotl-plugin · 36 tokens

writing-plans

Use after design approval to create a dated executable workflow file with bite-sized tasks, exact file paths, and loop/gate definitions.

yimwoo/hotl-plugin · 30 tokens