guide: Skill for Claude Code

.github/workflows/generate-ai-rules/skills/fix-guardrails/SKILL.md

fix-guardrails is a skill for Claude Code from rios0rios0/guide. It costs 50 tokens per session (2,896 once invoked), scanned A, original, MIT.

A workflow for resolving lint, test, and security-analysis findings across software repositories. Lint checks code style and common mistakes, tests check behavior, and SAST checks source code for security problems.

In plain words
What is it for?
Fixing `make lint`, `make test`, and `make sast` failures, detecting the code-hosting service, following repository change practices, and creating pull or merge requests when supported.
Why use it?
It turns several repository checks into one repeatable remediation process, including syncing code, fixing findings, updating documentation, and preparing a pull request.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: positional $N argument.

This is rios0rios0/guide's own configuration. It tells Claude Code how to work on guide itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything guide configures →

Part of the engineering-standards plugin — 5 skills, 8 commands, 7 agents shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to rios0rios0/guide. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/rios0rios0/guide/main/.github/workflows/generate-ai-rules/skills/fix-guardrails/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/rios0rios0/guide

Made for: Claude Code.

Or install engineering-standards, the plugin that ships this one along with the rest of its 5 skills, 8 commands, 7 agents.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for fix-guardrails

README.md
[![agentmods](https://agentmods.dev/badge/skills/rios0rios0/guide/fix-guardrails/github.svg)](https://agentmods.dev/skills/rios0rios0/guide/fix-guardrails)
Your own site
<a href="https://agentmods.dev/skills/rios0rios0/guide/fix-guardrails"><img src="https://agentmods.dev/badge/skills/rios0rios0/guide/fix-guardrails/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for fix-guardrails

Your own site · 80×15
<a href="https://agentmods.dev/skills/rios0rios0/guide/fix-guardrails"><img src="https://agentmods.dev/badge/skills/rios0rios0/guide/fix-guardrails.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,896 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00050 $0.02896
Opus 5 $0.00025 $0.01448
Sonnet 5 $0.00010 $0.00579
Haiku 4.5 $0.00005 $0.00290

Measured 9d ago against content hash 322a2967f74a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

fix-guardrails scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.github/workflows/generate-ai-rules/skills/fix-guardrails/SKILL.md · 262 lines

How it starts

The opening of the file, as written. The whole thing — 262 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Fix all guardrail findings (make lint, make test, make sast) across one or more repositories. This is a complete, repeatable workflow: sync with main, run all guardrails, fix every finding, update documentation, commit following standards, push, and create PRs.

For guardrail tools, refer to the CI/CD rule and Security rule. For commit conventions, refer to the Git Flow rule. For changelog updates, refer to the Documentation rule.

Vendor Detection

Auto-detect the Git hosting vendor from git remote get-url origin to determine the correct PR creation CLI:

Remote URL contains Vendor PR CLI
github.com GitHub gh pr create
dev.azure.com or ssh.dev.azure.com Azure DevOps az repos pr create
gitlab.com or gitlab GitLab glab mr create
Other Unknown Skip PR, report branch for manual creation

Step-by-step Workflow (repeat for every repository)

Step 1 -- Sync with the default branch

cd <REPO_PATH>
git checkout <default-branch>
git fetch --all
git pull --rebase
  • Detect the default branch with git symbolic-ref refs/remotes/origin/HEAD (strip refs/remotes/origin/). Fall back to main if unavailable.
  • If pull --rebase fails due to conflicts, report the failure and skip this repo.

Step 2 -- Run all three guardrails

Run them in this exact order. Each gate must be evaluated independently -- even if one passes, the others may fail.

Gate 1: Lint
make lint
  • Timeout: 3 minutes.
  • Parse the output. Record every finding with file path, line number, rule, and message.
  • NEVER invoke linter binaries directly. Always use make lint.

Read the full file on GitHub · 262 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 9d ago First seen · 262 lines · 50 tokens per session scan A 322a2967f74a

Subscribe to this mod's changes

fix-guardrails is a skill published in the GitHub repository rios0rios0/guide (2 stars, last pushed today), licensed MIT. It adds 50 tokens to every session and 2,896 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.