New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Red Teamer

by WeaveMindAI in WeaveMindAI/weft

Attacks a weft program before it faces the world, hunting every credible hole: an outsider lying through an input, a hallucination the graph trusts, a rogue step with agency, an unguarded path to…

Custom licenceAuto-check passed

Install Red Teamer

skills CLI
$ npx skills add WeaveMindAI/weft --skill red-teamer -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install WeaveMindAI/weft red-teamer --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/WeaveMindAI/weft.git skills-src && mkdir -p .claude/skills && cp -r skills-src/tangle/cline/.cline/skills/red-teamer .claude/skills/red-teamer && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
red-teamer
GitHub stars
2k
Token cost
~2.6k tokens
SKILL.md length
1,693 words
Files
1
Skills in repo
36
Repo updated
First seen
Licence
Custom licence

At a glance

Attacks a weft program before it faces the world, hunting every credible hole: an outsider lying through an input, a hallucination the graph trusts, a rogue step with agency, an unguarded path to…

  • Works in 5 steps: Read the program end to end:… → Map every [outside edge]: who can reach… → Map every [stake]. → …
  • SKILL.md covers Running commands, What you read and what you…, Objects and The attack catalog, plus 3 more sections
  • Calls node

What it does

Red Teamer is an agent skill from WeaveMindAI/weft. Attacks a weft program before it faces the world, hunting every credible hole: an outsider lying through an input, a hallucination the graph trusts, a rogue step with agency, an unguarded path to something that matters. Dispatched by Tangle when the program is high-stakes; reads the weft source, the prompts, and the node code, walks each attack from input to consequence, and reports verified findings with the layer that closes each. Never fixes, never runs the program, never edits.

Its SKILL.md is about 2.6k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: A programming language for AI orchestrations.

Example prompts

  • “Use the red-teamer skill to attack a weft program before it faces the world, hunting every credible hole: an outsider lying through an input, a…”
  • “/red-teamer”

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Read the program end to end: src/main.weft, the includes, the prompts, and the metadata of every node whose behavior the attacks will lean…
  2. Map every [outside edge]: who can reach each, and what each claims.
  3. Map every [stake].
  4. Sweep the nine objects of the catalog, one at a time, against the map. Every model call gets its prompt worst-cased with hostile input…
  5. Walk each candidate from its [outside edge] to its consequence in the source. It walks and is a [finding], or it is a [worry].

What it can do on your machine

Read from SKILL.md and the folder at commit 6e28f31. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • node

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Red Teamer loads about 2.6k tokens when it runs. Until then it costs about 124 tokens; SKILL.md has 1,693 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~124
When it runs · the whole SKILL.md, loaded when a task matches
~2.6k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 1,693 words (~2,582 tokens).

“You attack a weft program before it faces the world. What you miss, someone finds for real: a user who wants more than they asked for, a stranger who found the webhook, a message crafted to bend the model.”

— opening of SKILL.md by WeaveMindAI, Custom licence
name
red-teamer

Read the full SKILL.md on GitHub

Files

Just SKILL.md in tangle/cline/.cline/skills/red-teamer of WeaveMindAI/weft.

Open the folder on GitHubat commit 6e28f31

Compare with similar skills

Red Teamer next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Red Teamer compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Red Teamer this skillWeaveMindAI/weft2k—~2.6kAutomated safety check: PassCustom licence
Hunting For Dcsync Attacksmukul975/Anthropic-Cybersecurity-Skills34k—~897Automated safety check: PassApache-2.0
Hunting For Ntlm Relay Attacksmukul975/Anthropic-Cybersecurity-Skills34k—~718Automated safety check: PassApache-2.0
Hunting Credential Stuffing Attacksmukul975/Anthropic-Cybersecurity-Skills34k—~732Automated safety check: PassApache-2.0
Detecting Kerberoasting Attacksmukul975/Anthropic-Cybersecurity-Skills34k—~914Automated safety check: PassApache-2.0
Hunt Race Conditionsickn33/agentic-awesome-skills47k1 repos~5.7kAutomated safety check: PassMIT

Similar skills

  • Hunting For Dcsync Attacks

    mukul975/Anthropic-Cybersecurity-Skills

    Detect DCSync attacks (MITRE ATT&CK T1003.006) by analyzing Windows Event ID 4662 (AccessMask 0x100) for DS-Replication-Get-Changes and DS-Replication-Get-Changes-All requests issued by…

    34k GitHub stars~897 tokensUpdated 1 mo ago
    SecurityAuto-check passed

  • Hunting For Ntlm Relay Attacks

    mukul975/Anthropic-Cybersecurity-Skills

    Detects NTLM relay attacks (MITRE T1557.001) by analyzing Windows Event ID 4624 logon type 3 with NTLMSSP authentication, flagging IP-to-hostname mismatches, Responder/LLMNR poisoning signatures…

    34k GitHub stars~718 tokensUpdated 1 mo ago
    SecurityAuto-check passed

  • Hunting Credential Stuffing Attacks

    mukul975/Anthropic-Cybersecurity-Skills

    Detects credential stuffing attacks by analyzing authentication logs for login velocity anomalies, ASN diversity, password spray patterns, and geographic distribution of failed logins.

    34k GitHub stars~732 tokensUpdated 1 mo ago
    SecurityAuto-check passed

  • Detecting Kerberoasting Attacks

    mukul975/Anthropic-Cybersecurity-Skills

    Detect Kerberoasting attacks by monitoring for anomalous Kerberos TGS requests (Event ID 4769) targeting service accounts with SPNs, which attackers request offline to crack service account passwords.

    34k GitHub stars~914 tokensUpdated 1 mo ago
    SecurityAuto-check passed

  • Hunt Race Condition

    sickn33/agentic-awesome-skills

    Hunting skill for race condition vulnerabilities. An agent skill from sickn33/agentic-awesome-skills.

    47k GitHub starsUsed in 1 repo~5.7k tokens
    DevelopmentAuto-check passed

  • Hunting For Living Off The Cloud Techniques

    mukul975/Anthropic-Cybersecurity-Skills

    Hunts for adversary abuse of legitimate cloud services (Azure, AWS, GCP, and SaaS platforms) for command-and-control, data staging, and exfiltration, i.e.

    34k GitHub stars~925 tokensUpdated 1 mo ago
    SecurityAuto-check passed

More from WeaveMindAI/weft

All 36 skills in this repo

  • Weft Cloud Install

    WeaveMindAI/weft

    Read when the user wants weft itself on their Google Cloud for the first time, or to upgrade or resize the weft already there: getting the user's GitHub and Google Cloud accounts and CLIs ready, the…

    2k GitHub stars~2.4k tokensUpdated 2 days ago
    Auto-check passed

  • Weft Consumers

    WeaveMindAI/weft

    Read when the user wants their own website, app, bot or extension to list, show, answer, skip or cancel what a program is waiting on, fetch a file it carries, or show what one of its nodes is…

    2k GitHub stars~3.8k tokensUpdated 2 days ago
    Auto-check passed

  • Weft Deploying

    WeaveMindAI/weft

    Read when the user wants weft or a program live for real people on their cloud, asks about prod, a target, --on, a domain or GCP, or a deploy failed: targets and logging in, domains, the deploy…

    2k GitHub stars~4.2k tokensUpdated 2 days ago
    Auto-check: notes

  • Weft Metering

    WeaveMindAI/weft

    Read when the user asks what a run costs, or when a node is wired to a paid API weft does not already price: the three pieces of a custom paid service, a meter to copy, and the rules that keep a…

    2k GitHub stars~4k tokensUpdated 2 days ago
    Auto-check passed

  • Weft Sdp

    WeaveMindAI/weft

    Read when growing a program stage by stage: carving a run, supplying starting values, baking a trigger and firing it without activating, reusing completed work with a seed, freezing an accepted…

    2k GitHub stars~4k tokensUpdated 2 days ago
    Auto-check passed

  • Weft Frontend

    WeaveMindAI/weft

    Read when the user wants a page, app or site for the program, and before dispatching the frontend-builder: the verified scaffold commands, the default stack (pnpm, SvelteKit, PostgreSQL, BetterAuth…

    2k GitHub stars~8k tokensUpdated 2 days ago
    Auto-check: notes

Questions about Red Teamer

What does Red Teamer do?

Attacks a weft program before it faces the world, hunting every credible hole: an outsider lying through an input, a hallucination the graph trusts, a rogue step with agency, an unguarded path to…. Red Teamer is an agent skill from WeaveMindAI/weft. Attacks a weft program before it faces the world, hunting every credible hole: an outsider lying through an input, a hallucination the graph trusts, a rogue step with agency, an unguarded path to something that matters.

How do I install Red Teamer in Claude Code?

Run `npx skills add WeaveMindAI/weft --skill red-teamer -a claude-code`. Or copy the skill folder (tangle/cline/.cline/skills/red-teamer in WeaveMindAI/weft) into .claude/skills/red-teamer in your project. Claude Code loads it when a task matches its description.

How do I install Red Teamer in Codex?

Run `npx skills add WeaveMindAI/weft --skill red-teamer -a codex`. Or copy the skill folder (tangle/cline/.cline/skills/red-teamer in WeaveMindAI/weft) into .agents/skills/red-teamer in your project. Codex loads it when a task matches its description.

Can I use Red Teamer in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add WeaveMindAI/weft --skill red-teamer -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/red-teamer, .gemini/skills/red-teamer, .github/skills/red-teamer and .opencode/skills/red-teamer in your project.

What does Red Teamer need to run?

Going by SKILL.md and its folder, Red Teamer needs the command-line tools its instructions call (node).

Does Red Teamer access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Red Teamer safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Red Teamer use?

Red Teamer has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.

How many tokens does Red Teamer use?

About 2.6k tokens (SKILL.md is roughly 10k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Red Teamer?

Skills that share tags, products or a category with Red Teamer: Hunting For Dcsync Attacks (mukul975/Anthropic-Cybersecurity-Skills, 34k stars), Hunting For Ntlm Relay Attacks (mukul975/Anthropic-Cybersecurity-Skills, 34k stars), Hunting Credential Stuffing Attacks (mukul975/Anthropic-Cybersecurity-Skills, 34k stars) and Detecting Kerberoasting Attacks (mukul975/Anthropic-Cybersecurity-Skills, 34k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Red Teamer?

WeaveMindAI (a GitHub organization) maintains it in WeaveMindAI/weft, which has 1,995 GitHub stars. The repository holds 36 skills in this directory. The repository was last updated on October 6, 2026.

Source: WeaveMindAI/weft on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.