plan-and-verify

plan-and-verify is a skill for Claude Code, Codex from zhengbingquant/frontier-skills. It costs 143 tokens per session (2,944 once invoked), scanned A, original, MIT.

An engineering playbook for handling non-trivial code changes through defined planning, implementation, and verification stages.

In plain words
What is it for?
It helps set the scope, choose verification commands, establish a baseline, implement changes, run checks, and perform a final review for tasks involving multiple files, unfamiliar code, bugs, refactors, or migrations.
Why use it?
It reduces the risk of making changes without a clear way to prove they work. It also requires observed evidence before claiming success and treats failed tests as problems to investigate.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions CLAUDE.md; mentions AGENTS.md.

Good fit It helps set the scope, choose verification commands, establish a baseline, implement changes, run checks, and perform a final review for tasks involving multiple files, unfamiliar code, bugs, refactors, or migrations.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/zhengbingquant/frontier-skills/plan-and-verify
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 zhengbingquant/frontier-skills --skill plan-and-verify
Clone the repo
git clone --depth 1 https://github.com/zhengbingquant/frontier-skills

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 plan-and-verify

README.md
[![agentmods](https://agentmods.dev/badge/skills/zhengbingquant/frontier-skills/plan-and-verify/github.svg)](https://agentmods.dev/skills/zhengbingquant/frontier-skills/plan-and-verify)
Your own site
<a href="https://agentmods.dev/skills/zhengbingquant/frontier-skills/plan-and-verify"><img src="https://agentmods.dev/badge/skills/zhengbingquant/frontier-skills/plan-and-verify/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 plan-and-verify

Your own site · 80×15
<a href="https://agentmods.dev/skills/zhengbingquant/frontier-skills/plan-and-verify"><img src="https://agentmods.dev/badge/skills/zhengbingquant/frontier-skills/plan-and-verify.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 143 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,944 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 $0.00143 $0.02944
Opus 5 $0.00072 $0.01472
Sonnet 5 $0.00029 $0.00589
Haiku 4.5 $0.00014 $0.00294

Measured 10d ago against content hash 7fb7ade99509, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

plan-and-verify 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.

skills/plan-and-verify/SKILL.md · 234 lines

How it starts

The opening of the file, as written. The whole thing — 234 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Plan and Verify

This skill turns strong engineering judgment into mechanical rules. Follow the rules literally; do not substitute intuition for a rule unless the rule itself says so. The phases are ordered — do not skip forward.

0. The loop at a glance

Ground truth → Scope → Plan (verification named first) → Baseline → Implement → Verify → Final sweep → Report.

If you can hold only three rules in your head, hold these:

  1. Never write code before naming the command that will prove it works.
  2. Never claim anything you did not directly observe.
  3. When a test fails, assume your code is wrong — not the test.

1. Does this skill apply? Classify first

Apply the FIRST matching row:

Situation Path
Reading or explaining code, answering a question — no file or system state changes Skill does not apply
Single-file edit of ~20 lines or fewer, in a codebase whose test command you have already run successfully in this session Lightweight path (§8)
Anything else that changes files or system state Full playbook (§2–§7)

When in doubt, use the full playbook. Over-applying costs minutes; under-applying ships broken work. The words "quick", "simple", "just", or "tiny" in a request do NOT change the classification — misjudged quick fixes are where most damage happens.

2. Phase 0 — Ground truth

Never assume the stack, conventions, or state. Establish them by reading:

  1. Manifests first: pyproject.toml / package.json / Cargo.toml / go.mod / requirements.txt — whatever exists. This tells you language, dependencies, entry points, and tooling.
  2. Agent and human docs: AGENTS.md, CLAUDE.md, README.md, CONTRIBUTING.md, docs/. Project instructions override your defaults.
  3. How it is tested and run: look for a Makefile, bin/ or scripts/ folder, CI config (.github/workflows/), and test config (pytest.ini, [tool.pytest.ini_options]). Write down the exact test command.
  4. Safety check: could this environment be attached to production, real money, live traffic, or running services? Signals: broker/payment/cloud SDKs in dependencies, words like "live"/"production" in docs, running processes related to the repo, fresh files in logs/ or state directories. If ANY signal fires, stop and apply the live-system-guardrails skill (if available) before any state-changing command. If that skill is unavailable, treat every state-changing command as forbidden until you have direct evidence it is safe.

Read the full file on GitHub · 234 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 234 lines · 143 tokens per session scan A 7fb7ade99509

Subscribe to this mod's changes

plan-and-verify is a skill published in the GitHub repository zhengbingquant/frontier-skills (2 stars, last pushed 2mo ago), licensed MIT. It adds 143 tokens to every session and 2,944 once invoked, about $0.0007 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 2026-08-31.