red-team SKILL.md skillA

red-team from ljferrer/workauditrefine is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add ljferrer/workauditrefine/red-team@git:20261030.8fef1e1

Pins git:20261030.8fef1e1 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
ljferrer/workauditrefine
Path
skills/red-team/SKILL.md
Versions recorded
5
Latest version
git:20261030.8fef1e1, committed Oct 30, 2026
First version recorded
Sep 3, 2026
Size
34,894 bytes
Repository stars
11
License
MIT

Adversarially verify a proposed plan before you execute it. Reads the plan, derives a hybrid attack strategy (a universal spine + plan-specific probes), authors and runs a verification Workflow that PROVES claims by running them in throwaway sandboxes, then grills you on every blocker and patches the plan in place until the gate emits a proceed verdict — CLEARED, or ADJUDICATED when a patched blocker was not re-verified. Plan-agnostic — implementation plans, design specs, PRDs. Use when the…

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

# /red-team — harden a plan before you build it

You are the **Red Team Lead**. You attack a proposed plan, prove what is wrong by running it in throwaway sandboxes, and drive it to a **gate-emitted proceed verdict** — `CLEARED`, or `ADJUDICATED` when a blocker was patched but not re-verified ([ADR 0043](../../docs/adr/0043-adjudicated-clear-distinct-terminal-verdict.md)) — by grilling the user on blockers and patching the plan in place. You are the adversary to `writing-plans`. Reference: [references/lenses.md](references/lenses.md) — spine + probe catalog, schemas, severity rubric, report template.

This skill authorizes the **Workflow tool**: you adapt [assets/workflow-scaffold.js](assets/workflow-scaffold.js) and run it.

## Run
```
/red-team <plan-file> [--spec <file>] [--repo <path>] [--fast]
```
Default `<plan-file>` = the most recent `docs/plans/*.md`; `--repo` = cwd. **`--repo` routinely differs from the session cwd** — you can launch `/red-team` from one project's session to verify another project's plan. When it does, pass an absolute `<plan-file>` and `--repo`; the `--repo = cwd` default holds only when verifying the current project.

## Steps
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add ljferrer/workauditrefine/red-team@sha256:3cb82f8d41beee52

The line at the top of this page pins the label git:20261030.8fef1e1, 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_3krwd6xqip7oshxi.svg)](https://markdownregistry.com/a/art_3krwd6xqip7oshxi)

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

Versions

The registry has recorded 5 versions of this file, between Sep 3, 2026 and Oct 30, 2026, about one every 14 days.

versioncommittedcommitsizeaudit
git:20261030.8fef1e1 latest2026-10-30 8fef1e1 34,894 BA view · diff
git:20261030.89e9a462026-10-30 89e9a46 34,885 BA view · diff
git:20261021.12f06d02026-10-21 12f06d0 34,572 BA view · diff
git:20261021.93d202b2026-10-21 93d202b 34,180 BA view · diff
git:20260903.18c41be2026-09-03 18c41be 33,195 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 (34894 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

ljferrer/workauditrefine · 11 stars · license MIT · pushed 2026-11-04 · branch master

API

GET https://markdownregistry.com/api/v1/artifacts/art_3krwd6xqip7oshxi
GET https://markdownregistry.com/api/v1/resolve?ref=ljferrer/workauditrefine/red-team
GET https://markdownregistry.com/api/v1/blob/3cb82f8d41beee5268d3f122a1bc256c5a80f28aa4bda6f4298c82cdd0306270

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 ljferrer/workauditrefine

CLAUDE.md CLAUDE.md file
ljferrer/workauditrefine · CLAUDE.md
git:20261031.5d21f2a · audit A · 11 stars
aftermath SKILL.md skill
ljferrer/workauditrefine · skills/aftermath/SKILL.md · Evidence-gated cleanup after WAR work lands — delete stray WAR branches, reap orphaned run worktrees, close done…
git:20260806.b607909 · audit A · 11 stars
lessons-learned SKILL.md skill
ljferrer/workauditrefine · skills/lessons-learned/SKILL.md · Audit and tidy this project's Claude memory store (the MEMORY.md index plus its [[wikilinked]] topic files) — fan out…
git:20261030.b0f6bab · audit A · 11 stars
snipe SKILL.md skill
ljferrer/workauditrefine · skills/snipe/SKILL.md · Launch a quick one-shot audit — 1-5 read-only WAR auditor seats against the current changes, verdicts reported in chat…
git:20261031.145ae52 · audit A · 11 stars
survey-corps SKILL.md skill
ljferrer/workauditrefine · skills/survey-corps/SKILL.md · Survey this repo's memory lessons and open GitHub issues into war-shaped design specs — first mine qualifying hot…
git:20261030.b0f6bab · audit A · 11 stars
war-campaign SKILL.md skill
ljferrer/workauditrefine · skills/war-campaign/SKILL.md · Run a queue of WAR plans unattended — the hopper. Seeds a campaign ledger from an explicit plan list or a roadmap file…
git:20260904.5cc2f00 · audit A · 11 stars
war-help SKILL.md skill
ljferrer/workauditrefine · skills/war-help/SKILL.md · Print the WAR orientation card — what WAR is, the command set (/war-strategy → /war-room → /red-team → /war →…
git:20261031.5d21f2a · audit A · 11 stars
war-machine SKILL.md skill
ljferrer/workauditrefine · skills/war-machine/SKILL.md · Convert design specs into merged implementation plans plus a campaign roadmap — the middle step of the WAR pipeline…
git:20261030.0645294 · audit A · 11 stars
war-review SKILL.md skill
ljferrer/workauditrefine · skills/war-review/SKILL.md · Post-run telemetry and friction review for a completed /war run — reads the newest (or --run-pinned) run manifest under…
git:20261029.79dc6a0 · audit A · 11 stars
war-room SKILL.md skill
ljferrer/workauditrefine · skills/war-room/SKILL.md · Interview the user to produce a WAR run configuration at .claude/war/config.json — per-role model and reasoning effort…
git:20261104.8e648bd · audit A · 11 stars
war-strategy SKILL.md skill
ljferrer/workauditrefine · skills/war-strategy/SKILL.md · Two modes. Bare invoke runs the WAR plan-authoring interview itself, per the in-repo doctrine…
git:20261030.8fef1e1 · audit A · 11 stars
war SKILL.md skill
ljferrer/workauditrefine · skills/war/SKILL.md · Execute a detailed multi-phase implementation plan with a team of agents — Work, Audit, Refine, then capture learnings…
git:20261104.8e648bd · audit A · 11 stars

Every file in ljferrer/workauditrefine

Other files named red-team

red-team SKILL.md skill
borghei/claude-skills · engineering/red-team/SKILL.md · This skill should be used when the user asks to "plan a red team engagement", "scope a penetration test", "design a…
v1.0.0 · audit A · 1,019 stars
red-team SKILL.md skill
suboss87/fdeops · skills/red-team/SKILL.md · Stress-test a plan, brief or delivery claim against evidence and plausible failure modes. Use when the user asks for a…
git:20261005.ed7f271 · audit A · 947 stars
red-team SKILL.md skill
savvides/idstack · skills/red-team/SKILL.md · Adversarial course design audit across 5 dimensions: alignment stress test, evidence verification, cognitive load…
git:20261102.950ac90 · audit B · 27 stars
red-team SKILL.md skill
byerlikaya/claude-starter-kit · plugin/skills/red-team/SKILL.md · Attacker's-eye test of LLM/agent defenses: instruction hijacking, data exfiltration and tool abuse through untrusted…
git:20260924.a457823 · audit B · 26 stars
red-team SKILL.md skill
byerlikaya/claude-starter-kit · kit/skills/red-team/SKILL.md · Attacker's-eye test of LLM/agent defenses: instruction hijacking, data exfiltration and tool abuse through untrusted…
git:20260924.a457823 · audit B · 26 stars

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