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 lbk-open/super-spec --skill ss-guardrailsgit clone --depth 1 https://github.com/lbk-open/super-specWrote 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/lbk-open/super-spec/ss-guardrails)<a href="https://agentmods.dev/skills/lbk-open/super-spec/ss-guardrails"><img src="https://agentmods.dev/badge/skills/lbk-open/super-spec/ss-guardrails.svg" alt="Measured on agentmods" 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 | $0.00070 | $0.00511 |
| Opus 5 | $0.00035 | $0.00255 |
| Sonnet 5 | $0.00014 | $0.00102 |
| Haiku 4.5 | $0.00007 | $0.00051 |
Grade A, and why
ss-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 8d 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.
What it actually says
Guardrails
This skill is a reference library, not a workflow. Other skills read it at the point where they need to write, change, or review code; it has no standalone "run" behavior of its own.
What's Here
| File | Covers | Read When |
|---|---|---|
core.md |
Security baseline, code-review dimensions and severity levels, unit-testing principles, and anti-mistake rules for AI coding agents | Always — every coding or review task |
java.md |
Java exception handling and concurrency anti-patterns, JVM testing pitfalls | Project is Java/Kotlin/JVM |
go.md |
Go error handling and testing pitfalls | Project is Go |
cpp.md |
C++ memory safety, concurrency, error handling, and testing pitfalls | Project is C++ |
web.md |
Frontend/Node security and quality pitfalls | Project is TypeScript/JavaScript/web |
android.md |
Android-specific safety and quality pitfalls | Project is Android/Kotlin |
ios.md |
iOS-specific safety and quality pitfalls | Project is iOS/Swift |
flutter.md |
Flutter/Dart-specific safety and quality pitfalls | Project is Flutter |
How to Use This
- Detect the project's primary language/stack (build files, file extensions, existing code) or ask if it's ambiguous.
- Read
core.mdin full — it applies regardless of stack. - Read the one or two language files that match the project's stack. Skip the rest.
- Apply the checklists while writing code, and re-check against them during review, before claiming a task complete.
Treat this as read-only reference material: load it into context at the moment it's needed, apply it, and don't copy its contents into the user's repository. It carries no user-specific configuration and produces no output files of its own.
Failure Handling
If the project's stack isn't covered by any language file here, fall back to core.md alone and note the gap to the user rather than guessing at stack-specific rules that don't exist yet.
What ships with it
8 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.
- 8d ago First seen · 35 lines · 70 tokens per session scan A 48d88f11f615
ss-guardrails is a skill published in the GitHub repository lbk-open/super-spec (1 stars, last pushed 16d ago), licensed Apache-2.0. It adds 70 tokens to every session and 511 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
audit
Project health audit and health check — architecture, performance, tests, dependencies, code quality. Use when assessing overall project health, before releases, or after refactors.
review
Review code with parallel agents — tests, security, Ecto, LiveView, Oban. Use after implementation to catch bugs and anti-patterns before committing.
pr-review
Address feedback left on a GitHub pull request: fetch unresolved review threads, make agreed Elixir/Phoenix code fixes, reply, and resolve. Use for a PR URL/number or reviewer comments. NOT for pre-PR review, findings triage, or CI monitoring.
phx-pr-review
Address feedback left on a GitHub pull request: fetch unresolved review threads, make agreed Elixir/Phoenix code fixes, reply, and resolve. Use for a PR URL/number or reviewer comments. NOT for pre-PR review, findings triage, or CI monitoring.
boundaries
Analyze Phoenix context boundaries and module coupling via mix xref. Use when checking cross-context calls, validating dependencies, before splitting modules, or reviewing architecture.
challenge
Challenge mode reviews - rigorous questioning before approving changes. Use when you want thorough scrutiny of Ecto changes, LiveView events, OTP designs, or PR readiness.