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 rianvdm/product-ai-public --skill system-file-guardrailsgit clone --depth 1 https://github.com/rianvdm/product-ai-publicWrote 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/rianvdm/product-ai-public/system-file-guardrails)<a href="https://agentmods.dev/skills/rianvdm/product-ai-public/system-file-guardrails"><img src="https://agentmods.dev/badge/skills/rianvdm/product-ai-public/system-file-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/rianvdm/product-ai-public/system-file-guardrails"><img src="https://agentmods.dev/badge/skills/rianvdm/product-ai-public/system-file-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 | $0.00053 | $0.00946 |
| Opus 5 | $0.00026 | $0.00473 |
| Sonnet 5 | $0.00011 | $0.00189 |
| Haiku 4.5 | $0.00005 | $0.00095 |
Grade A, and why
system-file-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 12d 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
System File Edit Guardrails
Follow these checks when editing system files: commands (.opencode/command/), skills (.opencode/skills/), agents (.opencode/agent/), or AGENTS.md itself.
Before Editing
| Check | What to verify |
|---|---|
| Inbound references | Search for the file's name across .opencode/command/, .opencode/skills/, .opencode/agent/, and AGENTS.md. Note files whose assumptions could break if this file changes. |
| Outbound references | What skills, agents, or commands does this file reference? Verify each exists on disk. |
If broken outbound references are found, warn before proceeding (the edit might be fixing them).
After Editing a Command
| Check | What to verify |
|---|---|
| Frontmatter | description present |
$ARGUMENTS |
Parsed and handled (if command accepts arguments) |
| Skill loading | Lazy — no loading during research phases |
| Token efficiency | Compact tables over prose. Nothing duplicated from AGENTS.md |
| MCP tool references | Correct tool names, fallback behavior if tools are unavailable |
After Editing a Skill or Agent
| Check | What to verify |
|---|---|
| Frontmatter | name, description present. Agents: mode, tools also present |
| Description accuracy | Frontmatter description matches what the file actually does |
| Stale references | No references to commands, tools, files, or skills that don't exist |
| Agent quality checklist | Present and covers the agent's actual scope |
Writing the Content
The checks above cover mechanics. For the writing — what earns its place in a file that loads into every session — two references, which agree more than they appear to:
superpowers:writing-skills— TDD for documentation. Baseline-test first, and its Match the Form to the Failure table: prohibitions and rationalization tables work for discipline failures (agent knows the rule, skips it under pressure) and measurably backfire on shaping failures (output has the wrong form), where a positive recipe wins.- Matt Pocock's
writing-for-agents— the pruning lens. Read the real files, not the overview page:gh api repos/mattpocock/skills/contents/skills/productivity/writing-for-agents/SKILL.md --jq .content | base64 -d, plus its siblingSKILL-MECHANICS.mdfor frontmatter and the model- vs user-invoked choice. Five levers: context pointers (the pointer's wording, not its target, decides reliability — one trigger per branch), information hierarchy (in-file step → in-file reference → disclosed reference; inline what every branch needs, push behind a pointer what only some branches reach), completion criteria (checkable and exhaustive — "every rule applied" drives legwork where "produce a list" does not), leading words (a pretrained concept repeated as a token, never as a sentence), and pruning (the no-op test: delete the line, did behaviour change? If not, delete the whole sentence, not some words).
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.
- 12d ago First seen · 58 lines · 53 tokens per session scan A fa3e09d88693
system-file-guardrails is a skill published in the GitHub repository rianvdm/product-ai-public (16 stars, last pushed 4d ago), licensed MIT. It adds 53 tokens to every session and 946 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…