skillci-guardrails

skillci-guardrails is a skill for Claude Code from kabirnarang39/skillci. It costs 143 tokens per session (1,805 once invoked), scanned A, original, Apache-2.0.

A defensive writing and checking guide for Claude Skill files, which are instruction files that tell an AI agent how to handle tasks. It also covers the test cases and settings used to check those skills.

In plain words
What is it for?
Use it when creating, editing, or reviewing a SKILL.md file or its evaluation files. It helps write clear trigger descriptions, avoid unsafe commands and dependencies, and verify the result.
Why use it?
Skill files can fail quietly: the agent may follow unclear or unsafe instructions without showing an error. This guide helps authors prevent common security and discovery problems before testing.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the skillci plugin — 5 skills shipped together

Good fit Use it when creating, editing, or reviewing a SKILL.md file or its evaluation files. It helps write clear trigger descriptions, avoid unsafe commands and dependencies, and verify the result.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/kabirnarang39/skillci/skillci-guardrails
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add kabirnarang39/skillci --skill skillci-guardrails
Clone the repo
git clone --depth 1 https://github.com/kabirnarang39/skillci

Made for: Claude Code.

Or install skillci, the plugin that ships this one along with the rest of its 5 skills.

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 skillci-guardrails

README.md
[![agentmods](https://agentmods.dev/badge/skills/kabirnarang39/skillci/skillci-guardrails/github.svg)](https://agentmods.dev/skills/kabirnarang39/skillci/skillci-guardrails)
Your own site
<a href="https://agentmods.dev/skills/kabirnarang39/skillci/skillci-guardrails"><img src="https://agentmods.dev/badge/skills/kabirnarang39/skillci/skillci-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 skillci-guardrails

Your own site · 80×15
<a href="https://agentmods.dev/skills/kabirnarang39/skillci/skillci-guardrails"><img src="https://agentmods.dev/badge/skills/kabirnarang39/skillci/skillci-guardrails.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 143 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,805 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 $0.00143 $0.01805
Opus 5 $0.00072 $0.00903
Sonnet 5 $0.00029 $0.00361
Haiku 4.5 $0.00014 $0.00180

Measured 11d ago against content hash 5a64e3661732, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

skillci-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 11d 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.

skills/skillci-guardrails/SKILL.md · 141 lines

How it starts

The opening of the file, as written. The whole thing — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.

skillci guardrails

A SKILL.md is code: its frontmatter is an API, its body is an executable instruction set. It fails silently — a model just quietly does the wrong thing — rather than loudly, which makes both authoring it defensively and verifying it after the fact more important than for ordinary code, not less.

Step 1 — Author defensively, don't just lint afterward

These map directly to skillci's own static checks, so getting them right up front means Step 2 finds nothing instead of catching it after the fact:

  • description is the single field that decides whether this skill gets discovered and triggered at all — state what it does and when to use it, in language close to how a user would actually phrase the request. Keep it under 1024 characters (skillci flags longer — it eats into every caller's trigger-matching budget).
  • Never instruct piping a downloaded script straight into a shell interpreter, and never reference an unpinned :latest/@latest dependency — OWASP AST01/AST02, both real risk, not just lint noise.
  • Don't request network access to non-localhost hosts unless the skill's purpose requires it (AST03).
  • Never fetch remote content and tell the model to treat it as authoritative instructions (AST05) — use frontmatter's pinned_sources (a declared sha256, verifiable on request) instead.
  • Keep the body lean: under ~8000 characters, no exact-duplicate lines, no more than ~10 referenced files or ~100KB combined. Every extra line loads on every invocation.

Step 2 — Verify

Prefer calling skillci's own MCP tools directly if available in this session (check, eval, ...) over shelling out. Fall back to the CLI otherwise:

skillci check <path-to-skill-dir>
  1. Always run check — local-only, free, no API calls. Fix every finding, including Minor ones. If the repo pilots skillci non-blocking, --mode warn (or .skillci.yaml's lint.mode) reports without failing — still read and act on the output.
  2. If eval cases exist, run eval — confirms a trigger/behavior change actually works, not just that it reads plausibly.
  3. If eval cases don't exist and the skill is non-trivial, write at least one first. "Non-trivial" means: more than one trigger condition, any security-relevant behavior, or reuse beyond this session.
  4. If skillci isn't installed: go install github.com/kabirnarang39/skillci/cmd/skillci@latest (or see https://github.com/kabirnarang39/skillci#install). Install it, don't skip verification.

Read the full file on GitHub · 141 lines

Files

What ships with it

6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 11d ago First seen · 141 lines · 143 tokens per session scan A 5a64e3661732

Subscribe to this mod's changes

skillci-guardrails is a skill published in the GitHub repository kabirnarang39/skillci (8 stars, last pushed 28d ago), licensed Apache-2.0. It adds 143 tokens to every session and 1,805 once invoked, about $0.0007 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.

Related

Other skills, from other repositories

council

Run one request through several skills in parallel, isolated subagents, then merge their answers or judge the single best one. Use when the user invokes /council (or /council manage), or uses clear multi-skill-comparison language like "try this with a few different skills", "compare how different skills answer this"…

himanshufound/council · 135 tokens

configuration

A guide to configuring OpenClaw, including its main YAML configuration file, environment variables, performance settings, and security options.

chaterm/terminal-skills · 8 tokens

elasticsearch

Guidance for managing Elasticsearch, a search and data-storage system that organizes information into searchable indexes. It covers cluster health, nodes, shards, indexes, and related status APIs.

chaterm/terminal-skills · 8 tokens

sql-optimization

A guide to improving SQL queries, the commands used to read and change data in databases. It covers examining how MySQL and PostgreSQL execute queries and designing indexes that help them find data faster.

chaterm/terminal-skills · 10 tokens

ci-cd

A skill for configuring continuous integration and continuous delivery, or CI/CD: automated steps that build, test, and sometimes package or publish software when code changes. It includes examples for Jenkins, GitLab CI, and GitHub Actions.

chaterm/terminal-skills · 11 tokens

monitoring

A guide to monitoring systems with Prometheus and Grafana. Prometheus collects time-based measurements called metrics, while PromQL is the query language used to calculate values such as request rates, errors, resource use, and latency.

chaterm/terminal-skills · 8 tokens