A four-stage workflow for non-trivial coding work: plan, understand, develop, and optimize. It covers scope, code and tests to inspect, small changes, verification, and remaining risks.

Use it for features, bug fixes, refactors, releases, or other coding tasks that need a consistent quality process.

It reduces guessing, unintended changes, and unverified fixes by requiring context before editing and checks after editing. It can also preserve existing user changes.

pudo — Skill for Claude Code by DongDuong2001/pudo-code-system

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 DongDuong2001/pudo-code-system --skill pudo

Clone the repo

git clone --depth 1 https://github.com/DongDuong2001/pudo-code-system

Made for: Claude Code.

Or install pudo, the plugin that ships this one along with the rest of its 4 skills, 3 hooks.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/dongduong2001/pudo-code-system/pudo/github.svg)](https://agentmods.dev/skills/dongduong2001/pudo-code-system/pudo)

Your own site

<a href="https://agentmods.dev/skills/dongduong2001/pudo-code-system/pudo"><img src="https://agentmods.dev/badge/skills/dongduong2001/pudo-code-system/pudo/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/dongduong2001/pudo-code-system/pudo"><img src="https://agentmods.dev/badge/skills/dongduong2001/pudo-code-system/pudo.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 61 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 495 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.

Model	Per session	Once invoked
Fable 5.1	$0.00061	$0.00495
Opus 5.5	$0.00024	$0.00198
Sonnet 5.5	$0.00012	$0.00099
Haiku 4.5	$0.00006	$0.00049

Measured 3d ago against content hash 7cec7b578983, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

pudo 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 3d 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.

claude/plugin/skills/pudo/SKILL.md · 48 lines

What it actually says

PUDO

Work through four phases. For tiny edits (typo, one-line config) compress them, but still know what changes, change only that, and verify it.

1. Plan

Restate the goal. Write scope, out of scope, constraints and success criteria.
Name risks and anything destructive or ambiguous. Ask only when the answer changes what you build.

2. Understand

Read the files the change touches, their callers, tests and config before editing.
Never guess APIs, paths or file contents. Grep before calling something unused.

3. Develop

Small, scoped patches. Follow the patterns already in the codebase.
Preserve the user's existing changes. No new dependency without a reason.
Risky logic (a branch, a parser, security, data writes) gets a test that fails when it breaks.

4. Optimize

Run the relevant tests and checks. Report failures and skipped checks plainly.
Self-review the diff for edge cases, then list remaining risks.

Tools

When the pudo MCP server is connected:

pudo.runQualityGate with plan, understand, develop, optimize or release before moving to the next phase.
pudo.updateSessionHandoff (with confirmWrite: true) at checkpoints in long work, so another session can continue.
pudo.createContextPack to hand a bounded file set to another agent.
pudo.initProject previews by default; pass dryRun: false, confirmWrite: true only after the user agrees.

Enforcement

A Stop hook blocks finishing once when code was edited after the last test or check run. Run the checks, or say plainly why they cannot run.
Before context compaction a hook writes .pudo/auto-handoff.md and reloads it after.
Focused skills: /pudo:pudo-plan, /pudo:pudo-review, /pudo:pudo-handoff.

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.

3d ago First seen · 48 lines · 61 tokens per session scan A 7cec7b578983

Subscribe to this mod's changes

pudo is a skill published in the GitHub repository DongDuong2001/pudo-code-system (5 stars, last pushed 4d ago), licensed MIT. It adds 61 tokens to every session and 495 once invoked, about $0.0002 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 2026-10-24.

Planning Testing antigravity-skills claude-skills cursor-rules docs kiro-ide opencode-skills

playwright-cli

Automates browser interactions for testing and validating your own web applications using playwright-cli. Use when you need terminal-first browser control for navigation, form filling, screenshots, tracing, bound browser sessions, debugging, or generating Playwright test code. Only use against applications you own or…

testdino-hq/playwright-skill · 64 tokens

playwright-frontend

For frontend engineers authoring UI — how to make components reliably locatable by tests and AI agents. Covers the official Playwright locator priority, semantic/accessible markup first, and how to add valid, unique, stable data-testid attributes (naming convention, uniqueness in lists, stability rules) for React…

testdino-hq/playwright-skill · 92 tokens

playwright-qa

QA engineering workflows on top of Playwright. Use when a QA engineer asks to design test cases from a ticket, PRD or acceptance criteria, decide what to automate, write a bug report from a failing test or trace, convert manual test cases (TestRail, Xray, CSV) into Playwright specs with case-ID traceability, or review…

testdino-hq/playwright-skill · 83 tokens

pudo