Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/fmflurry/settings-opencodenpx agentmods add skills/fmflurry/settings-opencode/config-syncWrote 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/fmflurry/settings-opencode/config-sync)<a href="https://agentmods.dev/skills/fmflurry/settings-opencode/config-sync"><img src="https://agentmods.dev/badge/skills/fmflurry/settings-opencode/config-sync/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/fmflurry/settings-opencode/config-sync"><img src="https://agentmods.dev/badge/skills/fmflurry/settings-opencode/config-sync.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 | $0.00090 | $0.02871 |
| Opus 5.5 | $0.00036 | $0.01148 |
| Sonnet 5.5 | $0.00018 | $0.00574 |
| Haiku 4.5 | $0.00009 | $0.00287 |
Grade C, and why
config-sync scanned grade C with 2 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 4d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
1. First install: `~/.claude/settings.json` is seeded from the repo with defaults. Enumerates other installed skillsmediumAgent snooping
Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.
ls -la ~/.claude/skills/my-skill How it starts
The opening of the file, as written. The whole thing — 218 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Configuration Sync
Overview
This repo is the single source of truth for both OpenCode and Claude Code harness configuration. Never hand-edit the live directories (~/.config/opencode, ~/.claude). Always edit the repo first, then propagate via settings-sync (works from any directory) or bash install.sh --yes (from the repo root).
What Goes Where: Decision & Mapping Table
Verified directory structure:
- OpenCode target (
~/.config/opencode) receives: entire repo tree minus.claudeand excludes - Claude target (
~/.claude) receives: ONLY the allowlist from.claude/subtree - Skills are the only "edit once → both" case via union sync (root
skills/∪.claude/skills/, root wins)
| Item | Repo source location(s) | OpenCode | Claude | Edit location(s) | Notes |
|---|---|---|---|---|---|
| Agents (OpenCode) | opencode.jsonc (inline defs) + prompts/agents/*.txt (prompts) |
✓ | ✗ | opencode.jsonc or prompts/agents/ |
OpenCode-only. Agents defined inline in opencode.jsonc or as prompt templates. NO top-level agents/ dir exists. |
| Agents (Claude) | .claude/agents/ |
✗ | ✓ | .claude/agents/ |
Claude-only agent definitions. |
| Rules | .claude/rules/ |
✗ | ✓ | .claude/rules/ |
Claude-only rules (e.g., orchestration.md, verification-gate.md, codebase-exploration.md). |
| Hooks | .claude/hooks/ |
✗ | ✓ | .claude/hooks/ |
Claude-only runtime hooks (e.g., installed by learning runtime). |
| Harness scripts | scripts/agent-harness/ |
✓ | ⚠ | scripts/agent-harness/ |
Autonomy CLI (agent-harness) and helpers. OpenCode gets it through the tree copy. Claude hooks that call it need the installer to expose it; confirm in install.sh before relying on it. |
| Claude mods | .claude/mods/ |
✗ | ⚠ | .claude/mods/ |
Claude-only status line and UI mods. Reaches Claude only if the .claude/ allowlist in install.sh includes it; confirm there. |
| Commands | commands/ |
✓ | ✗ | commands/ |
OpenCode-only slash commands. |
| Prompts | prompts/ |
✓ | ✗ | prompts/ (including prompts/agents/ for agent prompts) |
OpenCode-only prompt templates. |
| Contexts | contexts/ |
✓ | ✗ | contexts/ |
OpenCode-only context definitions. |
| Tools | tools/ |
✓ | ✗ | tools/ |
OpenCode-only tool definitions. |
| Plugins | plugins/ |
✓ | ✗ | plugins/ |
OpenCode-only plugins. |
| Skills (shared) | skills/ (primary source) |
✓ | ✓ | skills/ |
The ONLY "edit once, both harnesses" type. Root skills/ wins on name conflict with .claude/skills/ via union sync. |
| Skills (Claude-only/override) | .claude/skills/ (secondary source) |
✓ | ✓ | .claude/skills/ |
Lower priority; root skills/ overrides. Both targets receive via union sync. |
| Harness config | opencode.jsonc |
✓ | ✗ | opencode.jsonc |
OpenCode harness configuration (models, providers, settings, agent defs). |
| Global instructions | .claude/CLAUDE.md + .claude/RTK.md |
✗ | ✓ | .claude/CLAUDE.md, .claude/RTK.md |
Claude-only global instructions and token-optimization guide. |
| Personal: settings.json | .claude/settings.json (seed) or settings.json (root seed, if exists) |
⚠ | ⚠ | Manual merge if needed | Seed-only; never overwritten on reinstall. Edit live copy or merge after repo changes. |
| Personal: settings.local.json | .claude/settings.local.json (seed) |
⚠ | ⚠ | Manual merge if needed | Seed-only; local overrides. |
| Personal: policy-limits.json | .claude/policy-limits.json (seed) |
⚠ | ⚠ | Manual merge if needed | Seed-only; rate limit policies. User edits in live dir will NOT propagate via reinstall. |
| *Personal: .local.json | *.local.json (seed) |
⚠ | ⚠ | Manual merge if needed | Seed-only; any other .local.json files. |
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.
- 4d ago Changed · +2 lines f118237ff4de
- 8d ago Changed 0141b27b58a2
- 13d ago Changed · +4 lines a38f9e7d97c0
- 1mo ago First seen · 212 lines · 90 tokens per session scan C 36dbeb5c3674
config-sync is a skill published in the GitHub repository fmflurry/settings-opencode (171 stars, last pushed yesterday), licensed MIT. It adds 90 tokens to every session and 2,871 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it C with 2 findings (reads agent configuration directories, enumerates other installed skills). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
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…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…