anvil
Heavy-duty "No-Vibes" debugging and hardening orchestrator.
Skill by grahama1970
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/grahama1970-anvil
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
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
- Runs as
- Shell scripts
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/anvil
What's inside
- Skill name
anvil- Description
- Heavy-duty "No-Vibes" debugging and hardening orchestrator. Use this for complex, stubborn bugs where `review-code` has failed, or for "Red Teaming" (hardening) a codebase. Runs multiple agents in parallel (Thunderdome) using git worktree isolation.
- License
- unknown
- Metadata
- short-description: Multi-agent Thunderdome for judging and fixing complex bugs
- Instructions
- 10 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
Files (4)
- SKILL.md
- pyproject.toml
- run.sh
- sanity.sh
The license isn't open source, so the instructions aren't shown here. Read SKILL.md on GitHub
More from grahama1970/agent-stack-public
- 0.524score
align
grahama1970
Round-based context alignment before execution.
SkillBFreshness: BClaude Code +9 - 0.524score
agentic-evals
grahama1970
Agentic evaluation of skills using multi-trial fixtures, deterministic command assertions, trajectory checks, safety constraints, and evidence-backed…
SkillBFreshness: BClaude Code +9 - 0.521score
agent-status
grahama1970
Artifact-driven status surfaces for long-running project-agent work.
SkillBFreshness: BClaude Code +9 - 0.519score
assess
grahama1970
Step back and critically reassess project state.
SkillBFreshness: BClaude Code +9 - 0.517score
assistant
grahama1970
Shared GPT + classifier inference gateway for persona monitor tasks.
SkillBFreshness: BClaude Code +9 - 0.516score
analytics
grahama1970
Flexible data science analytics for any dataset.
SkillBFreshness: BClaude Code +9 - 0.516score
analyze-elf
grahama1970
Reverse-engineer features from ELF binaries.
SkillBFreshness: BClaude Code +9 - 0.516score
agents-registry
grahama1970
Generate and query the centralized agent identity registry.
SkillBFreshness: BClaude Code +9 - 0.516score
batch-report
grahama1970
Generate post-run analysis reports for batch processing jobs.
SkillBFreshness: BClaude Code +9 - 0.516score
batch-quality
grahama1970
Pre-flight validation and quality gates for batch LLM operations.
SkillBFreshness: BClaude Code +9 - 0.513score
arxiv
grahama1970
Search arXiv for papers and extract knowledge into memory.
SkillBFreshness: BClaude Code +9 - 0.512score
agent-inbox
grahama1970
File-based inter-agent messaging with headless dispatch.
SkillBFreshness: BClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Sep 24, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- License unknown
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from grahama1970
- 0.524score
align
grahama1970
Round-based context alignment before execution.
SkillBFreshness: BClaude Code +9 - 0.524score
agentic-evals
grahama1970
Agentic evaluation of skills using multi-trial fixtures, deterministic command assertions, trajectory checks, safety constraints, and evidence-backed…
SkillBFreshness: BClaude Code +9 - 0.521score
agent-status
grahama1970
Artifact-driven status surfaces for long-running project-agent work.
SkillBFreshness: BClaude Code +9 - 0.519score
assess
grahama1970
Step back and critically reassess project state.
SkillBFreshness: BClaude Code +9 - 0.517score
assistant
grahama1970
Shared GPT + classifier inference gateway for persona monitor tasks.
SkillBFreshness: BClaude Code +9 - 0.516score
analytics
grahama1970
Flexible data science analytics for any dataset.
SkillBFreshness: BClaude Code +9
Cite this page
anvil skill. Agent Mart. https://agentmart.dev/skills/grahama1970-anvil (last updated 2026-10-24)