opencode-sync-sandbox

A sandbox-first workflow for changing and validating an OpenCode-synced plugin. It requires a plan, tests, local checks, and an isolated end-to-end run before the work is considered complete.

In plain words
What is it for?
Use it when modifying sync behavior, configuration handling, command execution, repository operations, or related paths, then review the test and end-to-end results.
Why use it?
It reduces the risk that changes to syncing, configuration, commands, or repository integration break existing behavior.

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/ihildy/opencode-synced/opencode-sync-sandbox
Any agent
npx skills add iHildy/opencode-synced --skill opencode-sync-sandbox
Clone the repo
git clone --depth 1 https://github.com/iHildy/opencode-synced

Made for: Claude Code, Codex.

Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 654 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 $0.00046 $0.00654
Opus 5 $0.00023 $0.00327
Sonnet 5 $0.00009 $0.00131
Haiku 4.5 $0.00005 $0.00065

Measured 2d ago against content hash 7f2265bb6d4d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

opencode-sync-sandbox 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.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/preflight.sh, scripts/run-e2e.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

.agents/skills/opencode-sync-sandbox/SKILL.md · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Opencode Sync Sandbox

Follow this workflow whenever a task changes sync behavior, config handling, command behavior, or repo/GitHub integration.

Required Workflow

  1. Create a concrete plan before editing files.
  2. Spawn as many subagents as useful for parallelizable work (tests, refactors, docs, investigations).
  3. Implement the change in small, reviewable steps.
  4. Add or update unit/regression tests for the behavior you changed.
  5. Run local checks:
    • bun run check
    • bun test
    • bun run build
  6. Run full isolated E2E before declaring success:
    • ./.agents/skills/opencode-sync-sandbox/scripts/run-e2e.sh
    • Run E2E variants that directly exercise the features changed in this task (for example: sessions, secrets, or other changed sync flags/paths).
  7. Report exact evidence: what changed, what tests ran, and an E2E artifact review.

Do not skip E2E for changes that affect sync workflows, path resolution, repo operations, or command execution.

E2E Reporting Requirements

  • Do not report the E2E artifact path unless the user explicitly asks for it.
  • Read results/summary.json, command result payloads under results/, and relevant logs/*.log tails.
  • Summarize the executed flow, pass/fail status, key warnings/errors, and any suspicious signals.
  • If warnings exist, explain whether they are expected, tolerated, or need follow-up.
  • For feature-flagged runs, report the exact artifact-level behavior for each changed feature (including restart requirements when relevant).

Sandbox Rules

  • Keep all E2E state inside .memory/e2e/runs/<run-id>/.
  • Never rely on shared global opencode directories for E2E assertions.
  • Use the harness-created isolated HOME/XDG sandboxes for each instance.
  • Use ephemeral GitHub repos for test runs; keep failed repos only when debugging is needed.

Upstream Reference Rule

Before changing integration-sensitive behavior, inspect upstream opencode source in:

  • .memory/opencode-upstream/opencode

Use this clone to confirm command/server/tool behavior and avoid assumptions.

Read the full file on GitHub · 65 lines

Files

What ships with it

3 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 · 65 lines · 46 tokens per session scan A 7f2265bb6d4d

Subscribe to this mod's changes

opencode-sync-sandbox is a skill published in the GitHub repository iHildy/opencode-synced (149 stars, last pushed 2d ago), licensed MIT. It adds 46 tokens to every session and 654 once invoked, about $0.0002 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