sec-minimal-trusted-code

sec-minimal-trusted-code is a skill for Claude Code, Codex from luisfurquim/wings. It costs 52 tokens per session (723 once invoked), scanned A, original, MPL-2.0.

A security design guide based on minimizing the amount of code that must be trusted to keep a system safe. It applies this idea to new features, dependencies, APIs, configuration, and build steps in the wings project.

In plain words
What is it for?
Reviewing or designing changes to wings, especially new packages, public interfaces, build processing, runtime parsing, and configuration options.
Why use it?
Every additional line, dependency, or processing path can contain bugs that affect security. Keeping trusted code small makes the security problem easier to review.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/luisfurquim/wings/sec-minimal-trusted-code
Any agent
npx skills add luisfurquim/wings --skill sec-minimal-trusted-code
Clone the repo
git clone --depth 1 https://github.com/luisfurquim/wings

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for sec-minimal-trusted-code

README.md
[![agentmods](https://agentmods.dev/badge/skills/luisfurquim/wings/sec-minimal-trusted-code.svg)](https://agentmods.dev/skills/luisfurquim/wings/sec-minimal-trusted-code)
Your own site
<a href="https://agentmods.dev/skills/luisfurquim/wings/sec-minimal-trusted-code"><img src="https://agentmods.dev/badge/skills/luisfurquim/wings/sec-minimal-trusted-code.svg" alt="Measured on agentmods" height="20"></a>
Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 723 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00052 $0.00723
Opus 5 $0.00026 $0.00362
Sonnet 5 $0.00010 $0.00145
Haiku 4.5 $0.00005 $0.00072

Measured 5d ago against content hash 3528b5c6e486, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sec-minimal-trusted-code 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 5d 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.

.claude/skills/sec-minimal-trusted-code/SKILL.md · 57 lines

How it starts

The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Minimal Trusted Code (djb)

Source philosophy: D. J. Bernstein, "Some thoughts on security after ten years of qmail 1.0". Security holes are bugs; the bug rate scales with the amount of code that must be correct for security to hold. Three levers, in order of power:

  1. Eliminate code. The most secure line is the one never written. Before adding a feature, ask what it costs in lines-that-must-be-right, not just in lines.
  2. Eliminate bugs in the code that remains. Smaller functions, explicit data flow, no hidden global state, exhaustive handling of every branch.
  3. Eliminate trusted code. Code may exist and still be untrusted: move risky work to where a bug cannot violate security.

How this maps to wings

  • Build-time vs runtime split is the qmail pattern. gen_i18n does all HTML/flex parsing at build time; the wasm runtime consumes pre-indexed JSON. Keep parsing OUT of the runtime. Any feature that tempts you to parse rich syntax inside the browser belongs in cmd/gen_i18n or cmd/build instead.
  • Misuse-resistant APIs (NaCl style). One call that is correct by default beats a toolkit of sharp primitives. Existing good examples to imitate: wi18n.SetCatalogPublicKey (one call → all-or-nothing signature enforcement), ApplySkin returning typed errors instead of panicking. A new API should have no "insecure but convenient" mode.
  • Dependencies are trusted code you didn't write. go.mod currently has 6 direct requires. Every candidate dep must answer: what does it replace, how many transitive deps does it drag in (go mod graph), could 50 lines of our own code do it? (See sec-supply-chain.)
  • Config options multiply states. Every WINGS_* env var or wings.json key doubles the test matrix. Prefer one good default over a knob.

Checklist for a new feature/API

  • Could this live at build time instead of runtime?
  • Is there a single entry point that is safe by default (no flag that disables verification, escaping, or validation)?
  • Does the public surface return error instead of panicking (input validation contract of this repo)?
  • Net lines of security-relevant code: did it shrink or grow? If it grew, is the growth isolated in one package with a narrow interface?
  • Zero new dependencies, or a written justification.

Read the full file on GitHub · 57 lines

Changes

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.

  1. 5d ago First seen · 57 lines · 52 tokens per session scan A 3528b5c6e486

Subscribe to this mod's changes

sec-minimal-trusted-code is a skill published in the GitHub repository luisfurquim/wings (29 stars, last pushed 1mo ago), licensed MPL-2.0. It adds 52 tokens to every session and 723 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

microsoft/ai-agents-for-beginners · 200 tokens

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…

vercel/next.js · 95 tokens

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…

vercel/next.js · 170 tokens

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…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens