opencode-audit

An audit tool for OpenCode, a system for configuring coding agents, commands, skills, plugins, and connections to external tools.

In plain words
What is it for?
It helps review an OpenCode setup, score its quality, identify risks, and create a prioritized remediation plan with usable configuration examples.
Why use it?
It finds configuration, safety, and operational problems and explains how to fix them.

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/awish021/opencode/opencode-audit
Any agent
npx skills add Awish021/opencode --skill opencode-audit
Clone the repo
git clone --depth 1 https://github.com/Awish021/opencode

Made for: Claude Code, Codex.

Per session 28 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 514 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 $0.00028 $0.00514
Opus 5 $0.00014 $0.00257
Sonnet 5 $0.00006 $0.00103
Haiku 4.5 $0.00003 $0.00051

Measured 2d ago against content hash 05b5562ff6d3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

opencode-audit 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 2d 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.

skills/opencode-audit/SKILL.md · 67 lines

What it actually says

OpenCode Audit Skill

What this skill does

This skill runs a practical OpenCode audit and outputs:

  • a 100-point score with grade
  • category-by-category findings
  • concrete, ready-to-use commands and config snippets
  • a short remediation plan

When to use

Use this skill when the user asks to:

  • audit OpenCode setup quality
  • improve OpenCode safety and permissions
  • review agents, commands, skills, MCP, or plugins
  • prepare a hardening checklist before team rollout

Required inputs

  • Target repo or config path
  • Optional focus area (permissions, agents, skills, runtime checks)

Audit workflow

  1. Load references/OPENCODE-AUDIT.md.
  2. Discover project and global OpenCode files.
  3. Score all 8 rubric categories.
  4. Build prioritized findings with evidence paths.
  5. Produce copy-paste remediation snippets.
  6. Return total score, grade, and 7-day plan.

Discovery checklist

  • AGENTS.md, .opencode/AGENTS.md, ~/.config/opencode/AGENTS.md
  • .opencode/config.json, .opencode/opencode.json, .opencode/opencode.jsonc
  • ~/.config/opencode/config.json, ~/.config/opencode/opencode.json, ~/.config/opencode/opencode.jsonc
  • .opencode/agents/*.md, ~/.config/opencode/agents/*.md
  • .opencode/commands/*.md, ~/.config/opencode/commands/*.md
  • .opencode/skills/*/SKILL.md, ~/.config/opencode/skills/*/SKILL.md
  • .claude/skills/*/SKILL.md, ~/.claude/skills/*/SKILL.md when present
  • MCP and plugin sections in config

Output contract

Return in this order:

  1. Total score and grade.
  2. Category scores.
  3. Top findings with severity.
  4. Ready-to-use fixes.
  5. 7-day action plan.

Guardrails

  • Stay OpenCode-specific; do not use non-OpenCode terminology unless compatibility paths are relevant.
  • Do not invent files; only cite discovered paths.
  • Keep fixes actionable and minimal.
  • Prefer least-privilege recommendations for permissions.
Files

What ships with it

2 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.

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. 2d ago First seen · 67 lines · 28 tokens per session scan A 05b5562ff6d3

Subscribe to this mod's changes

opencode-audit is a skill published in the GitHub repository Awish021/opencode (11 stars, last pushed 2mo ago), licensed MIT. It adds 28 tokens to every session and 514 once invoked, about $0.0001 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

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

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

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…

microsoft/vscode · 71 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