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.
npx skills add kabirnarang39/skillci --skill skillci-guardrailsgit clone --depth 1 https://github.com/kabirnarang39/skillciWrote 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/kabirnarang39/skillci/skillci-guardrails)<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.
<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>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 | $0.00143 | $0.01805 |
| Opus 5 | $0.00072 | $0.00903 |
| Sonnet 5 | $0.00029 | $0.00361 |
| Haiku 4.5 | $0.00014 | $0.00180 |
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.
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:
descriptionis 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/@latestdependency — 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 declaredsha256, 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>
- 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'slint.mode) reports without failing — still read and act on the output. - If eval cases exist, run
eval— confirms a trigger/behavior change actually works, not just that it reads plausibly. - 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.
- 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.
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.
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.
- 11d ago First seen · 141 lines · 143 tokens per session scan A 5a64e3661732
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.
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"…
configuration
A guide to configuring OpenClaw, including its main YAML configuration file, environment variables, performance settings, and security options.
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.
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.
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.
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.