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.
curl -O https://raw.githubusercontent.com/rios0rios0/guide/main/.github/workflows/generate-ai-rules/skills/fix-guardrails/SKILL.mdgit clone --depth 1 https://github.com/rios0rios0/guideWrote 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.
[](https://agentmods.dev/skills/rios0rios0/guide/fix-guardrails)<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.
<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>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.
| Model | Per session | Once 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 |
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.
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(striprefs/remotes/origin/). Fall back tomainif unavailable. - If
pull --rebasefails 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.
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.
- 9d ago First seen · 262 lines · 50 tokens per session scan A 322a2967f74a
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.
Other skills, from other repositories
change-impact-analysis
Perform a deterministic, graph-driven Change Impact Analysis for a repository. Given a set of changed files, builds a dependency graph, finds directly and transitively affected modules, validates API contracts for breaking changes, parses CODEOWNERS, and computes a 0-100 deployment risk score. Trigger on: change…
systematic-debugging
4-phase root cause debugging: understand bugs before fixing.
triage-issues
Triage GitHub issues in the googleapis/mcp-toolbox repo: propose the correct labels (type / priority / product / status), check for duplicates, verify a bug has enough info to act on, and draft a triage comment. Use whenever a maintainer asks you to triage, label, categorize, prioritize, or "look at" an issue (or a…
copilotkit-debug
Use when diagnosing CopilotKit issues -- runtime connectivity failures, agent not responding, streaming errors, tool execution problems, transcription failures, version mismatches, and AG-UI event tracing.
agent-merge-conflict-arbiter
Neutral arbiter for merge conflicts between two agents.
python-debugpy
Debug Python: pdb REPL + debugpy remote (DAP).