team-security SKILL.md skillA

team-security from gonimar/claude-web-studio is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add gonimar/claude-web-studio/team-security@git:20260927.f32d805

Pins git:20260927.f32d805 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
gonimar/claude-web-studio
Path
skills/team-security/SKILL.md
Versions recorded
5
Latest version
git:20260927.f32d805, committed Sep 27, 2026
First version recorded
Sep 26, 2026
Size
5,813 bytes
Repository stars
5
License
MIT

Full security cycle: threat-model refresh → security-audit (code) → dependency-audit → harden (perimeter/containers) → optional pentest of the project's own app → consolidated report and stories. Use before release or after adding auth/payments/uploads/multiplayer.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Team: Security

Reply in the project conversation language (CLAUDE.md → Language); code, identifiers, paths and commit messages stay in English.

File writes and any mutation (git, deploy) happen only after an explicit "May I write?" / "Proceed?" — each one `AskUserQuestion` (proceed (Recommended) · show the draft/diff first · not now) → "yes". After the "write" answer: `touch .claude/.write-consent` (rule 7 — the consent-guard hook checks the marker). A partial report on BLOCKED at any stage is mandatory.

**Consent for delegated work is collected by this skill.** A subagent spawned through `Task` cannot ask the user. Before each `Task` batch, the "Proceed?" question names the agents and the files each will create or change (audit reports, threat-model updates); that answer covers those files. A delegated step that needs to go beyond its brief (another file, a code or configuration change, a production mutation) stops and reports it, and the parent asks.
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add gonimar/claude-web-studio/team-security@sha256:a1e2b4ef481b2021

The line at the top of this page pins the label git:20260927.f32d805, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_yvpxc5lpdhlash5i.svg)](https://markdownregistry.com/a/art_yvpxc5lpdhlash5i)

2 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 5 versions of this file, between Sep 26, 2026 and Sep 27, 2026, more than one a day.

versioncommittedcommitsizeaudit
git:20260927.f32d805 latest2026-09-27 f32d805 5,813 BA view · diff
git:20260926.947eac02026-09-26 947eac0 5,834 BA view · diff
git:20260926.85fc6e62026-09-26 85fc6e6 5,751 BA view · diff
git:20260926.dbae8f92026-09-26 dbae8f9 5,416 BA view · diff
git:20260926.4537cad2026-09-26 4537cad 4,832 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (5813 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

gonimar/claude-web-studio · 5 stars · license MIT · pushed 2026-09-27 · branch master

API

GET https://markdownregistry.com/api/v1/artifacts/art_yvpxc5lpdhlash5i
GET https://markdownregistry.com/api/v1/resolve?ref=gonimar/claude-web-studio/team-security
GET https://markdownregistry.com/api/v1/blob/a1e2b4ef481b20215008a282ae011cb509beff94f35c7d7ec055c69c9bb7e728

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from gonimar/claude-web-studio

CLAUDE.md CLAUDE.md file
gonimar/claude-web-studio · CLAUDE.md
git:20260927.56b0a9a · audit A · 5 stars
a11y-audit SKILL.md skill
gonimar/claude-web-studio · skills/a11y-audit/SKILL.md · Audits accessibility against WCAG 2.2 AA — axe-core via Playwright, Lighthouse a11y, a manual keyboard/screen-reader…
git:20260927.54cdcbc · audit A · 5 stars
adopt SKILL.md skill
gonimar/claude-web-studio · skills/adopt/SKILL.md · Brownfield onboarding — detects the real stack of an existing project (Go/PHP/Node, Angular/Vue/Nuxt, GraphQL/REST…
git:20260927.be1f3bd · audit A · 5 stars
api-contract SKILL.md skill
gonimar/claude-web-studio · skills/api-contract/SKILL.md · Designs the API contract before implementation — GraphQL SDL by default (types, Node/connections, inputs, mutations…
git:20260927.f32d805 · audit A · 5 stars
architecture-decision SKILL.md skill
gonimar/claude-web-studio · skills/architecture-decision/SKILL.md · Creates an Architecture Decision Record (context, ≥2 options with costs, decision, consequences, verification) or…
git:20260927.f32d805 · audit A · 5 stars
architecture-review SKILL.md skill
gonimar/claude-web-studio · skills/architecture-review/SKILL.md · Cross-checks ADRs, API contracts, data model, threat model and feature specs for consistency and feasibility, with…
git:20260927.d019450 · audit A · 5 stars
backlog SKILL.md skill
gonimar/claude-web-studio · skills/backlog/SKILL.md · Records an idea, wish or suggestion that nobody has decided to act on as one line in production/backlog.md and stops —…
git:20260927.c816400 · audit A · 5 stars
brainstorm SKILL.md skill
gonimar/claude-web-studio · skills/brainstorm/SKILL.md · Explores a product or web-game idea before specification — audience, problem, competitors, constraints…
git:20260927.f32d805 · audit A · 5 stars
changelog SKILL.md skill
gonimar/claude-web-studio · skills/changelog/SKILL.md · Generates or updates CHANGELOG.md from Conventional Commits since the last tag (Keep a Changelog format, SemVer bump…
git:20260927.f32d805 · audit A · 5 stars
code-review SKILL.md skill
gonimar/claude-web-studio · skills/code-review/SKILL.md · Reviews the branch's diff (`--diff`, the PR's changes) or given files for correctness, standards, ADR adherence, OWASP…
git:20260927.d019450 · audit A · 5 stars
collaboration-protocol SKILL.md skill
gonimar/claude-web-studio · skills/collaboration-protocol/SKILL.md · The collaboration protocol every Web Studio agent follows (context first, ask, options, draft before writing…
git:20260927.d082861 · audit A · 5 stars
create-stories SKILL.md skill
gonimar/claude-web-studio · skills/create-stories/SKILL.md · Slices a feature spec into implementable vertical-slice stories (contract → backend → frontend/game → tests) with…
git:20260927.d019450 · audit A · 5 stars

Every file in gonimar/claude-web-studio

Browse by kind, by grade A, or by owner.