Borrowing it
Nothing to install: this file belongs to sdeonvacation/opencode-x. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/sdeonvacation/opencode-x/main/.agents/skills/add-experimental-feature/SKILL.mdgit clone --depth 1 https://github.com/sdeonvacation/opencode-xWrote 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/sdeonvacation/opencode-x/add-experimental-feature)<a href="https://agentmods.dev/skills/sdeonvacation/opencode-x/add-experimental-feature"><img src="https://agentmods.dev/badge/skills/sdeonvacation/opencode-x/add-experimental-feature/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/sdeonvacation/opencode-x/add-experimental-feature"><img src="https://agentmods.dev/badge/skills/sdeonvacation/opencode-x/add-experimental-feature.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00017 | $0.01314 |
| Opus 5.5 | $0.00007 | $0.00526 |
| Sonnet 5.5 | $0.00003 | $0.00263 |
| Haiku 4.5 | $0.00002 | $0.00131 |
Grade A, and why
add-experimental-feature 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 1mo 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 — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context
opencode-x has ~30 experimental features. Each needs: a schema entry, a gating check, optionally a TUI command gate, and guide/test updates. Three different default patterns exist — getting this wrong ships a feature silently enabled or permanently disabled.
Default Pattern Decision
| Desired default | Pattern | Example |
|---|---|---|
| ON by default (most features) | cfg.experimental?.X !== false |
goal_system, swarm, workflow |
| OFF by default (risky/large) | cfg.experimental?.X === true |
deep_research, wire_diagnostics |
| Numeric default | cfg.experimental?.X ?? N |
tool_result_budget ?? 50_000 |
Steps
1. Add schema entry — src/config/config.ts
Find the experimental object schema (around line 1693). Add:
// Default-on boolean:
my_feature: z.boolean().optional().describe("Enable my feature"),
// Opt-in boolean:
my_feature: z.boolean().optional().describe("Enable my feature (opt-in)"),
// Numeric with default:
my_feature_budget: z.number().int().positive().optional().describe("Budget for my feature (default: 50000)"),
Tunables (model, limits) are fine to keep as separate keys. Only add a boolean gate if the feature itself needs an on/off switch.
2. Gate the tool — src/tool/registry.ts
Find the tool list around line 199:
// Default-on:
...(cfg.experimental?.my_feature !== false ? [MyTool] : []),
// Opt-in:
...(cfg.experimental?.my_feature === true ? [MyTool] : []),
3. Gate behavior in session — src/session/prompt.ts or src/session/processor.ts
Use the same pattern as step 2 wherever the feature is invoked in the session loop.
4. Gate TUI slash command — src/cli/cmd/tui/app.tsx
CRITICAL: SDK type mismatch. The sync.data.config type comes from @opencode-ai/sdk/v2 and may not include new experimental keys. Always cast through any:
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.
- 1mo ago First seen · 144 lines · 17 tokens per session scan A 1a14e6ba5fa1
add-experimental-feature is a skill published in the GitHub repository sdeonvacation/opencode-x (81 stars, last pushed 2d ago), licensed MIT. It adds 17 tokens to every session and 1,314 once invoked, about $0.0001 per session on Opus 5.5. 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.
Other skills, from other repositories
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.