guardrails
Rendered guardrail framework: keep a repo's hard rules in one-rule-per-file GRL sources behind a compact router, and render only the rules a task needs.
Skill by bolasblack
Chalk Labs
Need help deploying guardrails?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
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/bolasblack-guardrails
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: ml, writing, productivity
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 and code. Checked Nov 1, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
- Runs as
- Node.js package
Network hosts it talks to 2
bun.sh· found in codecodeload.github.com· found in install command
Files it touches
~/.claude/skills/guardrails
What's inside
- Skill name
guardrails- Description
- Rendered guardrail framework: keep a repo's hard rules in one-rule-per-file GRL sources behind a compact router, and render only the rules a task needs. Use when gathering guardrail context before implementing or reviewing code, when creating, editing, retiring, or reviewing GRL rule files or .agents/guardrails/index.md, when running the guardrails CLI (validate, render, review-metadata, next-id), or when setting up, adopting, or bootstrapping a guardrail framework in a repo that does not have one yet. Do NOT use for ordinary lint rule authoring unless the lint rule backs a guardrail, for runtime safety guardrails such as rate limiting, destructive-command protection, or input validation, for LLM or AI output guardrails, or for soft conventions and style preferences that are not hard rules.
- License
- unknown
- Compatibility
- Requires Bun (https://bun.sh) to run scripts/guardrails.ts. review-metadata additionally requires git.
- Instructions
- 75 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
Files (32)
- CHANGELOG.md
- README.md
- SKILL.md
- VERSION
- adoption.md · references/
- auditing.md · references/
- authoring.md · references/
- consuming.md · references/
- design-rationale.md · references/
- active-rule-removed.md · references/review-metadata-instructions/
- enforcement.md · references/review-metadata-instructions/
- lint-assist-reason.md · references/review-metadata-instructions/
- parse-issue.md · references/review-metadata-instructions/
- references.md · references/review-metadata-instructions/
- retire-reason.md · references/review-metadata-instructions/
- retired-rule-text.md · references/review-metadata-instructions/
- router.md · references/review-metadata-instructions/
- rule-text.md · references/review-metadata-instructions/
- skip-index-reason.md · references/review-metadata-instructions/
- reviewing.md · references/
- rule-change-workflow.md · references/
- schema.md · references/
- tooling.md · references/
- guardrails.test.ts · scripts/
- guardrails.ts · scripts/
- package.json · scripts/
- tsconfig.json · scripts/
- agent-instructions-snippet.md · templates/
- index.md · templates/
- GRL-1.md · templates/rules/
- GRL-2.md · templates/rules/
- GRL-3.md · templates/rules/
The license isn't open source, so the instructions aren't shown here. Read SKILL.md on GitHub
More from bolasblack/claude-skills
- 0.609score
agent-centric
bolasblack
Track decisions (AGD) with validation and indexing.
SkillAFreshness: A★ 4Claude Code +9 - 0.569score
codex
bolasblack
OpenAI Codex second opinion via the codex CLI — three modes.
SkillBFreshness: B★ 4Claude Code +9 - 0.569score
grok
bolasblack
xAI Grok second opinion via the grok CLI — three modes.
SkillBFreshness: B★ 4Claude Code +9 - 0.569score
git-hook
bolasblack
Assess, adopt, or harden repository-local Git-hook automation.
SkillBFreshness: B★ 4Claude Code +9 - 0.569score
mcp-skill-generator
bolasblack
Convert MCP servers to Claude Code skills with progressive disclosure.
SkillBFreshness: B★ 4Claude Code - 0.564score
grill-me
bolasblack
Stress-test a plan, design, decision, or idea through a focused interview.
SkillBFreshness: B★ 4Claude Code +9 - 0.546score
create-verification-skill
bolasblack
Generate a project-local verification skill that drives your app the way a user does — any language, framework, or platform.
SkillBFreshness: B★ 4Claude Code +9 - 0.541score
maintain-verification-skill
bolasblack
Periodic pass that keeps a project's verification skill and feature map honest: parallel source readers per feature, one live session driving every feature…
SkillBFreshness: B★ 4Claude Code +9 - 0.519score
design-md
bolasblack
Create, update, validate, diff, or export DESIGN.md files following the Google Stitch DESIGN.md spec and @google/design.md tooling.
SkillCFreshness: C★ 4Claude Code +9 - 0.519score
dependency-safety-check
bolasblack
Screens third-party project dependencies for known vulnerabilities and supply-chain risk before installation using a bundled check-deps.py script.
SkillCFreshness: C★ 4Claude Code +9 - 0.454score
command-creator
bolasblack
Guide for creating Claude Code slash commands.
SkillDFreshness: D★ 4Claude Code +9 - 0.454score
pi-extension-dev
bolasblack
End-to-end workflow for developing, debugging, configuring, and shipping pi-coding-agent extensions and pi packages.
SkillDFreshness: D★ 4Claude Code +9
Signals
- Stars
- 4
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Sep 16, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- License unknown
- Repository
- github.com/bolasblack/claude-skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from bolasblack
- 0.609score
agent-centric
bolasblack
Track decisions (AGD) with validation and indexing.
SkillAFreshness: A★ 4Claude Code +9 - 0.569score
mcp-skill-generator
bolasblack
Convert MCP servers to Claude Code skills with progressive disclosure.
SkillBFreshness: B★ 4Claude Code - 0.569score
grok
bolasblack
xAI Grok second opinion via the grok CLI — three modes.
SkillBFreshness: B★ 4Claude Code +9 - 0.569score
git-hook
bolasblack
Assess, adopt, or harden repository-local Git-hook automation.
SkillBFreshness: B★ 4Claude Code +9 - 0.569score
codex
bolasblack
OpenAI Codex second opinion via the codex CLI — three modes.
SkillBFreshness: B★ 4Claude Code +9 - 0.564score
grill-me
bolasblack
Stress-test a plan, design, decision, or idea through a focused interview.
SkillBFreshness: B★ 4Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get guardrails running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
guardrails skill. Agent Mart. https://agentmart.dev/skills/bolasblack-guardrails (last updated 2026-10-24)