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.
npx skills add znlgis/my-opencode-deepseek-config --skill verify-with-docsgit clone --depth 1 https://github.com/znlgis/my-opencode-deepseek-configWrote 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/znlgis/my-opencode-deepseek-config/verify-with-docs)<a href="https://agentmods.dev/skills/znlgis/my-opencode-deepseek-config/verify-with-docs"><img src="https://agentmods.dev/badge/skills/znlgis/my-opencode-deepseek-config/verify-with-docs.svg" alt="Measured on agentmods" 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 | $0.00094 | $0.01033 |
| Opus 5 | $0.00047 | $0.00517 |
| Sonnet 5 | $0.00019 | $0.00207 |
| Haiku 4.5 | $0.00009 | $0.00103 |
Grade A, and why
verify-with-docs 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 8d 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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verify With Docs (Retrieval-First)
Your training data has a cutoff and libraries move fast, so for any code that touches a specific dependency, retrieve before you write. Prefer retrieval over pre-training memory — never trust the model's memorized API surface when the current docs are reachable.
When this applies
Reach for this skill when the task:
- implements against a named library/framework/SDK, especially a fast-moving one (web frameworks, cloud SDKs, AI/LLM SDKs, build tools, ORMs);
- depends on exact signatures, option names, return shapes, or config keys;
- says "latest", "current", "did X change in version Y", or names a version;
- is failing with an error that looks like a wrong/renamed API.
Skip it for stable stdlib usage you are certain of, or pure logic with no external API surface.
References Local-First
Before fetching from the web, check if the target library is available as a
local reference in opencode.jsonc → references. If mounted (e.g., via
references: { "opencode": { "repository": "anomalyco/opencode" } }), read
the source code from the local clone first. Only fall back to web fetch if:
- The reference is outdated (commit older than the version in use)
- The reference does not cover the relevant code paths
- No reference is mounted for the target library
The loop
- Pin the exact version. Read the version actually in use before reading any
docs — the docs must match it.
- JS/TS:
package.json+ the lockfile (node_modules/<pkg>/package.jsonis the ground truth for the installed version). - Python:
pyproject.toml/requirements.txt/pip show <pkg>. - Go:
go.mod. Rust:Cargo.toml/Cargo.lock.
- JS/TS:
- Go to the primary source, matched to that version. Prefer, in order:
official docs for that version → the library's own repo (tag/branch matching
the version) → typed definitions shipped with the package (
.d.ts, stubs, godoc) → reputable references. Skip blog posts and Q&A for signatures. - Extract only what you need. The exact signature, required vs optional params, return type, error modes, and any breaking-change note between the installed version and what memory assumes. Don't dump whole pages into context — quote the minimal relevant lines.
- Report verified facts with citations. Every signature you hand back must carry a source URL or file path so the implementing agent can trust it.
- Only then implement — against the retrieved API, not the remembered one.
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.
- 8d ago First seen · 99 lines · 94 tokens per session scan A f5f6f36915ab
verify-with-docs is a skill published in the GitHub repository znlgis/my-opencode-deepseek-config (57 stars, last pushed yesterday), licensed MIT. It adds 94 tokens to every session and 1,033 once invoked, about $0.0005 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.
Other skills, from other repositories
skill-creator
Create, install, or update skills in the workspace. Use when (1) installing a skill from a URL or remote source, (2) creating a new skill from scratch, (3) updating or restructuring existing skills. Always use this skill for any skill installation or creation task.
ralplan
Consensus planning entrypoint that auto-gates vague ralph/autopilot/team requests before execution.
remember
Review reusable project knowledge and decide what belongs in project memory, notepad, or durable docs.
image-generator
Generate or edit images from text and local files, image URLs, or data URLs through image API. Use when the user asks to create an image, generate from one or more reference images, combine styles or elements across references, or edit a marked region while blending the result into the original scene.
weibo-poster
A writing guide for Weibo, a Chinese microblogging platform similar to a short-post social network. It covers concise posts, longer posts, hashtags, @ mentions, image layouts, and posting-time suggestions.
xiaohongshu-writer
A writing guide for Xiaohongshu, a Chinese social platform for short lifestyle and advice posts. It helps shape titles, post structure, emoji use, cover text, and hashtags.