05-skills

05-skills is a cursor rule for Cursor from WellApp-ai/Well. It costs 611 tokens per session, scanned A, original, MIT.

A guide to reusable skills stored in a project's .cursor/rules/skills/ folder. It lists skills for tasks such as setup, debugging, code review, browser testing, creating MCP integrations, and planning product work.

In plain words
What is it for?
Use it to choose a skill for environment setup, systematic debugging, code review, web-app testing, workflow diagrams, product research, or similar listed tasks.
Why use it?
It helps an agent find the right task-specific instructions instead of treating every request as a general coding problem.

Cursor rule for Cursor

Written for Cursor: a Cursor rule (.mdc).

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 rules/wellapp-ai/well/05-skills
Clone the repo
git clone --depth 1 https://github.com/WellApp-ai/Well

Made for: Cursor.

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 05-skills

README.md
[![agentmods](https://agentmods.dev/badge/rules/wellapp-ai/well/05-skills.svg)](https://agentmods.dev/rules/wellapp-ai/well/05-skills)
Your own site
<a href="https://agentmods.dev/rules/wellapp-ai/well/05-skills"><img src="https://agentmods.dev/badge/rules/wellapp-ai/well/05-skills.svg" alt="Measured on agentmods" height="20"></a>
Per session 611 This file is loaded in full into every session.
When invoked 611 The same file — it is already loaded in full.
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 5.1 $0.00611 $0.00611
Opus 5 $0.00305 $0.00305
Sonnet 5 $0.00122 $0.00122
Haiku 4.5 $0.00061 $0.00061

Measured 6d ago against content hash 91b5c4df8b10, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

05-skills 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 6d 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.

cursor-rules/rules/05-skills.mdc · 49 lines

How it starts

The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skills

Skills are reusable capability modules in .cursor/rules/skills/.

Available Skills

Skill Trigger Purpose
setup "use setup skill" One-time environment setup
mcp-server "use mcp-server skill" Create new MCP integrations
webapp-testing "use webapp-testing skill" Browser/Storybook testing
skill-creator "use skill-creator skill" Create new skills
debug "use debug skill" Systematic debugging
code-review "use code-review skill" Review code against rules
hotfix "use hotfix skill" Urgent production fixes
bpmn-workflow "use bpmn-workflow skill" Generate BPMN diagrams from features
problem-framing "use problem-framing skill" JTBD job stories, HMW questions
competitor-scan "use competitor-scan skill" Research best-in-class products
design-context "use design-context skill" Refresh UI context from design system
state-machine "use state-machine skill" Document UI component states
qa-planning "use qa-planning skill" Gherkin scenarios, acceptance criteria
dependency-mapping "use dependency-mapping skill" DSM matrix, risk scoring
gtm-alignment "use gtm-alignment skill" Align phases with GTM strategy
phasing "use phasing skill" Group slices into phases with timeline
team-routing "use team-routing skill" Detect domain, find owner
slack-announce "use slack-announce skill" Generate team announcements
notion-sync "use notion-sync skill" Standardize Notion updates
tech-divergence "use tech-divergence skill" Technical options, Gate 4
pr-review "use pr-review skill" Code validation before commit
qa-commit "use qa-commit skill" Verify QA Contract (G#N, AC#N)
pr-threshold "use pr-threshold skill" Auto-trigger PR on threshold
test-hardening "use test-hardening skill" Convert Gherkin to tests
decision-capture "use decision-capture skill" Capture patine at Gates
session-status (auto) Breadcrumb, takt, muda tracking
autonomous-loop "ralph mode", "keep going" Iterate until success with Jidoka
compliance-audit "use compliance-audit skill" Audit Value Delivery compliance post-PR

Read the full file on GitHub · 49 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. 6d ago First seen · 49 lines · 611 tokens per session scan A 91b5c4df8b10

Subscribe to this mod's changes

05-skills is a cursor rule published in the GitHub repository WellApp-ai/Well (340 stars, last pushed 29d ago), licensed MIT. It adds 611 tokens to every session, about $0.0031 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.