self-update

self-update is a skill for Claude Code, Codex from CoffeeCheese/easy-prd-testing. It costs 90 tokens per session (733 once invoked), scanned A, original, MIT.

An updater for the complete Easy PRD Testing installation, including its skills and plugin. It first checks the available release and then uses the repository’s documented updater to apply the change safely.

In plain words
What is it for?
Use it to check the installed version and upgrade, update, or synchronize the Easy PRD Testing installation. It is not for updating test cases, test environments, or XMind files.
Why use it?
It avoids improvised copying or overwriting when keeping the testing tools current. It also prevents updates during an active testing workflow and checks that the required Node.js version is available.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/coffeecheese/easy-prd-testing/self-update
Any agent
npx skills add CoffeeCheese/easy-prd-testing --skill self-update
Clone the repo
git clone --depth 1 https://github.com/CoffeeCheese/easy-prd-testing

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 self-update

README.md
[![agentmods](https://agentmods.dev/badge/skills/coffeecheese/easy-prd-testing/self-update.svg)](https://agentmods.dev/skills/coffeecheese/easy-prd-testing/self-update)
Your own site
<a href="https://agentmods.dev/skills/coffeecheese/easy-prd-testing/self-update"><img src="https://agentmods.dev/badge/skills/coffeecheese/easy-prd-testing/self-update.svg" alt="Measured on agentmods" height="20"></a>
Per session 90 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 733 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00090 $0.00733
Opus 5 $0.00045 $0.00367
Sonnet 5 $0.00018 $0.00147
Haiku 4.5 $0.00009 $0.00073

Measured 4d ago against content hash 10c7ce25340f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

self-update 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 4d 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/self-update/SKILL.md · 59 lines

How it starts

The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Self Update

Use the repository updater as the only mutation engine. Keep version discovery read-only, show the confirmed release before changing files, and never improvise copy, pull, or overwrite commands.

Route The Request

  • Treat phrases such as “升级版本”, “更新 Skills”, “同步最新版”, and “检查插件更新” as update intent when the object or current context is Easy PRD Testing.
  • When the update object is ambiguous, ask whether the user means the complete Easy PRD Testing installation.
  • For negated, hypothetical, or explanatory requests, explain the behavior without running the updater.
  • Do not route “更新测试用例”, “升级测试环境”, XMind refreshes, or product-version testing here.

Check Before Confirmation

  1. Do not update while the current conversation is in execution-gate, test-execution, result-aggregation, or regression-testing. Ask the user to finish or stop that active workflow first.
  2. Resolve the repository root from this file as ../... Do not scan for other installations.
  3. Require Node.js 18 or newer. If it is unavailable, tell the user how to install it; never install it automatically.
  4. Run the read-only check:
node <repository-root>/scripts/easy-prd-testing.mjs check --json
  1. If the installation is current, ahead, incompatible, symlinked, incomplete, or unsupported, report the returned reason and stop. Do not invent a fallback mutation.
  2. When an update is available, show the installation path and type, current and target versions, 3–5 release highlights, the Release Notes link, and any local changes.

Confirm Once

  • Ask one explicit question to install the displayed target release.
  • If a managed installation contains local modifications, state that a successful update permanently deletes them and does not keep a backup. Treat only an explicit acceptance of that loss as force authorization.
  • Never force-update a Git installation with changes.
  • Do not treat a vague acknowledgement as permission to add --force.

Install The Confirmed Release

Read the full file on GitHub · 59 lines

Files

What ships with it

1 file 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. 4d ago First seen · 59 lines · 90 tokens per session scan A 10c7ce25340f

Subscribe to this mod's changes

self-update is a skill published in the GitHub repository CoffeeCheese/easy-prd-testing (2 stars, last pushed 23d ago), licensed MIT. It adds 90 tokens to every session and 733 once invoked, about $0.0005 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.

Related

Other skills, from other repositories