ai-coding-agent-guardrails SKILL.md skillB

This file is byte-identical to the first copy the registry indexed. Same content hash, so the same checks give both the same grade.

ai-coding-agent-guardrails from francostino/opencode-skills-collection is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add francostino/opencode-skills-collection/ai-coding-agent-guardrails@v1.0

Pins v1.0 in mdr.lock. Pin the fingerprint instead.

Audit grade
B, 16 of 17 checks passed
Kind
SKILL.md skill
Repository
francostino/opencode-skills-collection
Path
bundled-skills/ai-coding-agent-guardrails/SKILL.md
Versions recorded
1
Latest version
v1.0, committed Sep 21, 2026
Size
13,002 bytes
Repository stars
87
License
MIT

Secure AI coding agents (Claude Code, Cursor, Codex, Copilot) with permission.

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

# AI Coding Agent Guardrails

Secure the use of AI coding agents across engineering teams. This skill covers permission boundaries, secret protection, sandbox isolation, code review gates, and audit trails for Claude Code, Cursor, Copilot, and Codex.

---

## Permission Boundaries

### CLAUDE.md Configuration

Create a `CLAUDE.md` at the repository root to restrict Claude Code behavior:

```markdown
# CLAUDE.md

## Restrictions

- NEVER read or output contents of .env, .env.*, secrets.yaml, or any file matching *.pem, *.key
- NEVER execute `rm -rf`, `DROP TABLE`, `kubectl delete`, or `terraform destroy` commands
- NEVER push directly to main or master branches
- NEVER modify files in the infrastructure/, terraform/, or .github/workflows/ directories without explicit user approval
- NEVER install new dependencies without listing them first for review
- NEVER access or display API keys, tokens, passwords, or connection strings

## Allowed Operations

- Read and modify application source code in src/, lib/, and tests/
- Run test suites with `npm test`, `pytest`, `go test`
- Run linters with `eslint`, `ruff`, `golangci-lint`
- Create new branches with prefix `ai/` or `agent/`
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add francostino/opencode-skills-collection/ai-coding-agent-guardrails@sha256:0de7f7a1bb34ab9d

The line at the top of this page pins the label v1.0, 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_sd6g2xppp23oar4t.svg)](https://markdownregistry.com/a/art_sd6g2xppp23oar4t)

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

Versions

The registry has recorded 1 version of this file, committed on Sep 21, 2026.

versioncommittedcommitsizeaudit
v1.0 latest2026-09-21 846b6b5 13,002 BB view

Audit of the latest version

B  16 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • fail: No instruction to read or print local credentials (matched: read or output contents of .env, .env)
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (13002 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 base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Starting a new one? Use a template for SKILL.md on mdpantry, which passes every one of these checks and says what to change in it.

Source

GitHub

francostino/opencode-skills-collection · 87 stars · license MIT · pushed 2026-10-18 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_sd6g2xppp23oar4t
GET https://markdownregistry.com/api/v1/resolve?ref=francostino/opencode-skills-collection/ai-coding-agent-guardrails
GET https://markdownregistry.com/api/v1/blob/0de7f7a1bb34ab9d7c9bebbf2cac9f8380eb9f03a404d9e96ccea5dcab28046e

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 francostino/opencode-skills-collection

AGENTS.md AGENTS.md file
francostino/opencode-skills-collection · AGENTS.md
git:20260820.c2f6bd5 · audit A · 87 stars
00-andruia-consultant SKILL.md skill
francostino/opencode-skills-collection · bundled-skills/00-andruia-consultant/SKILL.md · Usar al iniciar o mejorar un proyecto de IA: diagnostica código y restricciones, propone skills existentes y redacta…
git:20261015.fac8b7e · audit A · 87 stars
007 SKILL.md skill
francostino/opencode-skills-collection · bundled-skills/007/SKILL.md · Security audit, hardening, threat modeling (STRIDE/PASTA), Red/Blue Team, OWASP checks, code review, incident response…
git:20260906.7d37dc9 · audit A · 87 stars
10-andruia-skill-smith SKILL.md skill
francostino/opencode-skills-collection · bundled-skills/10-andruia-skill-smith/SKILL.md · Usar para crear o mejorar una skill de Andru.ia: define entradas y resultados, redacta SKILL.md con ejemplos y límites…
git:20261015.fac8b7e · audit A · 87 stars
20-andruia-niche-intelligence SKILL.md skill
francostino/opencode-skills-collection · bundled-skills/20-andruia-niche-intelligence/SKILL.md · Usar tras definir el sector de un proyecto: prepara un dossier en español con contexto, normas aplicables, patrones UX…
git:20261015.fac8b7e · audit A · 87 stars
2slides-ppt-generator SKILL.md skill
francostino/opencode-skills-collection · bundled-skills/2slides-ppt-generator/SKILL.md · AI-powered presentation generation via the 2slides API — create slides from text, match a reference image style…
git:20260906.7d37dc9 · audit A · 87 stars
360-feedback-system SKILL.md skill
francostino/opencode-skills-collection · bundled-skills/360-feedback-system/SKILL.md · 360 feedback register: reviewer, subject, review cycle, visibility, due date and score, as CSV, SQL, JSON Schema or…
git:20261001.ed2b2ec · audit A · 87 stars
3d-web-experience SKILL.md skill
francostino/opencode-skills-collection · bundled-skills/3d-web-experience/SKILL.md · Use when building or debugging web 3D scenes, product configurators or portfolios with Three.js, React Three Fiber or…
git:20261015.fac8b7e · audit A · 87 stars
aas-compose-stack SKILL.md skill
francostino/opencode-skills-collection · bundled-skills/aas-compose-stack/SKILL.md · Preserve the coding agent's explicit AAS skill selection as a validated stack and optional evidence.
git:20261004.4720433 · audit A · 87 stars
aas-discover SKILL.md skill
francostino/opencode-skills-collection · bundled-skills/aas-discover/SKILL.md · Discover AAS skills for an explicit task and compare their complete instructions without installing them.
git:20261004.4720433 · audit A · 87 stars
aas-review-stack SKILL.md skill
francostino/opencode-skills-collection · bundled-skills/aas-review-stack/SKILL.md · Review AAS stack manifests, preview plans and selection evidence in Workbench without applying changes.
git:20261004.4720433 · audit A · 87 stars
ab-test-setup SKILL.md skill
francostino/opencode-skills-collection · bundled-skills/ab-test-setup/SKILL.md · Use when designing an A/B or split test: define the hypothesis, control and variants, estimate sample size, verify…
git:20260906.7d37dc9 · audit A · 87 stars

Every file in francostino/opencode-skills-collection

Other files named ai-coding-agent-guardrails

ai-coding-agent-guardrails SKILL.md skill
sickn33/agentic-awesome-skills · plugins/agentic-awesome-skills-claude/skills/ai-coding-agent-guardrails/SKILL.md · Secure AI coding agents (Claude Code, Cursor, Codex, Copilot) with permission
v1.0 · audit B · 48,329 stars

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