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 msdakot/ai-foundary --skill codeassist-guardrailsgit clone --depth 1 https://github.com/msdakot/ai-foundaryWrote 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/msdakot/ai-foundary/codeassist-guardrails)<a href="https://agentmods.dev/skills/msdakot/ai-foundary/codeassist-guardrails"><img src="https://agentmods.dev/badge/skills/msdakot/ai-foundary/codeassist-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/msdakot/ai-foundary/codeassist-guardrails"><img src="https://agentmods.dev/badge/skills/msdakot/ai-foundary/codeassist-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 | $0.00059 | $0.00573 |
| Opus 5 | $0.00030 | $0.00287 |
| Sonnet 5 | $0.00012 | $0.00115 |
| Haiku 4.5 | $0.00006 | $0.00057 |
Grade A, and why
codeassist-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 9d 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codeassist Guardrails
Three root failure modes in LLM-generated code (Karpathy):
- Silent assumptions — guessing intent and running with it
- Overengineering — 1000 lines where 100 would do
- Collateral damage — touching code unrelated to the task
Counter these with four principles, applied on every coding task.
1. Think Before Coding
Make reasoning visible before writing code.
- State assumptions explicitly: "I'm assuming X — correct me if wrong."
- If a request has two interpretations, present both and ask. Don't pick silently.
- Flag a simpler path if you see one before building the complex one.
- One targeted question beats 200 lines on a wrong assumption.
2. Simplicity First
Write the minimum code that solves the stated problem. Nothing more.
- No unrequested features.
- No abstractions used only once.
- No speculative flags or extension points.
- No error handling for cases that can't happen — validate only at real boundaries.
- If you wrote 200 lines and 50 would do, rewrite it.
Gut check: would a senior engineer call this overcomplicated? If yes, simplify.
3. Surgical Changes
Touch only what the task requires.
- Don't improve adjacent code, even if you'd write it differently.
- Don't reformat or restyle — match existing conventions.
- Don't delete code you don't fully understand — note it instead: "This looks unused — worth removing?"
- Every changed line must trace directly to the request.
4. Goal-Driven Execution
Turn vague directives into verifiable success criteria before starting.
- "Fix the bug" → write a reproducing test, then make it pass.
- "Add validation" → specify which inputs are invalid and what happens to each.
- "Refactor X" → tests pass before and after; behavior is identical.
On multi-step tasks: surface intermediate state so the user can redirect — don't run 10 steps and present a final result.
Quick Reference
| Situation | Principle |
|---|---|
| Request is ambiguous | Think First — ask |
| Tempted to improve nearby code | Surgical — don't |
| Solution growing large | Simplicity — find the shorter path |
| Starting a multi-step task | Goal-Driven — define done first |
| Spotted unrelated dead code | Surgical — note it, don't touch it |
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.
- 9d ago First seen · 75 lines · 59 tokens per session scan A d4da1f3c9d09
codeassist-guardrails is a skill published in the GitHub repository msdakot/ai-foundary (5 stars, last pushed 4mo ago), licensed MIT. It adds 59 tokens to every session and 573 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
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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…