red-team
Red-team the current plan with the read-only skeptic subagent before any code is written.
Skill by bioassembly
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/bioassembly-red-team
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/red-team
What's inside
- Skill name
red-team- Description
- Red-team the current plan with the read-only skeptic subagent before any code is written. Use after planning, before implementation, or on /red-team.
- License
- MIT
- Instructions
- 10 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Red-team the plan 1. No plan stated in this conversation (and no implementation_plan artifact) → ask for it in one sentence and stop. 2. `invoke_subagent` with TypeName `skeptic` (fall back to `research`), passing the plan verbatim, the repo context it touches (paths, constraints), and: "Attack this plan: failure modes, hidden assumptions, simpler alternatives. Maximum 5 attacks, each with the cheapest check that would refute it." 3. Report the findings verbatim. 4. Close with `Revise the plan, then re-run /red-team.` or `Plan holds. Proceed to build.` Attack only — do not start implementing.
From bioassembly/antigravity-sage, MIT.
More from bioassembly/antigravity-sage
- 0.570score
fair-data-principles
bioassembly
Enforce and audit FAIR data principles (Findable, Accessible, Interoperable, Reusable) across scientific datasets, bioinformatics workflows, metadata…
SkillAFreshness: AClaude Code +9 - 0.565score
skill-evaluation
bioassembly
Evaluate and benchmark skills, prompts, or model changes with test cases, assertions, and quantitative comparison.
SkillAFreshness: AClaude Code +9 - 0.565score
first-principles-explainer
bioassembly
Break down complex bioinformatics, data engineering, and algorithmic pipelines from first principles.
SkillAFreshness: AClaude Code +9 - 0.565score
github-repo-best-practices
bioassembly
Create or audit GitHub repositories and READMEs to top-1% standard.
SkillAFreshness: AClaude Code +9 - 0.565score
skill-maker
bioassembly
Author, edit, or evaluate agent skills to best-practice standard by researching top skills repos and testing against real failures.
SkillAFreshness: AClaude Code +9 - 0.565score
pipeline-sketch-results
bioassembly
Consolidate and organize outputs from custom, multi-step sketch/bash/python pipelines into a clean, numbered, user-facing results/ deliverable directory while…
SkillAFreshness: AClaude Code +9 - 0.565score
security-audit
bioassembly
Audit a PHP/CodeIgniter 4 web app for OWASP Top-10 vulnerabilities (SQLi, XSS, CSRF, IDOR, session, upload, secrets).
SkillAFreshness: AClaude Code +9 - 0.565score
skill-acquisition
bioassembly
Search online for a trusted, best-practice skill and install it locally when no existing skill covers the task.
SkillAFreshness: AClaude Code +9 - 0.561score
checkpoint
bioassembly
Dump current task state to NOTES.md in the working directory so work survives context compaction or a session restart.
SkillAFreshness: AClaude Code +9 - 0.561score
agentic-coding
bioassembly
Working agreements for coding agent loops — plan-then-edit, minimal diffs, verify each step.
SkillAFreshness: AClaude Code +9 - 0.558score
pdf-inplace-editing
bioassembly
In-place PDF editing/anonymization, zero layout drift — content-stream swaps, raster re-lettering, pixel-diff verified.
SkillAFreshness: AClaude Code +9 - 0.556score
doctor
bioassembly
Run health diagnostics on the Antigravity harness (MCP endpoints, Serena LSP, skills count, custom subagents, rules, permissions).
SkillAFreshness: AClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Oct 8, 2026 (21 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/bioassembly/antigravity-sage
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from bioassembly
- 0.570score
fair-data-principles
bioassembly
Enforce and audit FAIR data principles (Findable, Accessible, Interoperable, Reusable) across scientific datasets, bioinformatics workflows, metadata…
SkillAFreshness: AClaude Code +9 - 0.565score
security-audit
bioassembly
Audit a PHP/CodeIgniter 4 web app for OWASP Top-10 vulnerabilities (SQLi, XSS, CSRF, IDOR, session, upload, secrets).
SkillAFreshness: AClaude Code +9 - 0.565score
pipeline-sketch-results
bioassembly
Consolidate and organize outputs from custom, multi-step sketch/bash/python pipelines into a clean, numbered, user-facing results/ deliverable directory while…
SkillAFreshness: AClaude Code +9 - 0.565score
first-principles-explainer
bioassembly
Break down complex bioinformatics, data engineering, and algorithmic pipelines from first principles.
SkillAFreshness: AClaude Code +9 - 0.565score
github-repo-best-practices
bioassembly
Create or audit GitHub repositories and READMEs to top-1% standard.
SkillAFreshness: AClaude Code +9 - 0.565score
skill-acquisition
bioassembly
Search online for a trusted, best-practice skill and install it locally when no existing skill covers the task.
SkillAFreshness: AClaude Code +9
Cite this page
red-team skill. Agent Mart. https://agentmart.dev/skills/bioassembly-red-team (last updated 2026-10-24)