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 agentmods add skills/znlgis/my-opencode-deepseek-config/opencode-confignpx skills add znlgis/my-opencode-deepseek-config --skill opencode-configgit 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/opencode-config)<a href="https://agentmods.dev/skills/znlgis/my-opencode-deepseek-config/opencode-config"><img src="https://agentmods.dev/badge/skills/znlgis/my-opencode-deepseek-config/opencode-config.svg" alt="Measured on agentmods" 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 | $0.00076 | $0.01195 |
| Opus 5 | $0.00038 | $0.00598 |
| Sonnet 5 | $0.00015 | $0.00239 |
| Haiku 4.5 | $0.00008 | $0.00120 |
Grade C, and why
opencode-config scanned grade C with 1 finding 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 today.
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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- Default-allow, deny the dangerous: `deny` `.env*` reads (except `.env.example`); `ask` on destructive bash (`rm -rf`, `git push -f`, `git reset --hard`, PowerShell/cmd equivalents) and `external_directory`. Cover shell How it starts
The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenCode Config Authoring
For generic opencode config shapes, see the built-in customize-opencode skill;
this file only covers this repository's local conventions.
Repository layout
| Path | Role |
|---|---|
opencode.jsonc |
Global config: model, permissions, plugins, agents, commands, compaction |
AGENTS.md |
Global rules auto-loaded into every agent's context |
agents/<name>.md |
One custom agent per file (frontmatter + system prompt) |
skills/<name>/SKILL.md |
On-demand skills, auto-discovered from the config dir |
Hard constraints
- Only
deepseek/deepseek-v4-pro,deepseek/deepseek-v4-flash, and the multimodaldeepseek/deepseek-v4-flash-vision-exp. Never a fourth model; vision-exp is for visual input only, never a default. - Use the singular keys (
plugin,snapshot), not the fork's plural (plugins,snapshots).
Config key shapes (authoritative)
- references — alias →
{"repository" | "path", "branch"?, "description"?}.repositorytakes a Git URL / host-path /owner/repo(+branchto pin a ref);pathtakes relative / absolute /~/;descriptiontells agents when to use it. String shorthand ("alias": "../docs") allowed. - skills.paths — extra skill dirs:
"skills": { "paths": ["../shared-skills"] }; supports~/and relative paths;skills.urlspulls remote skills. - agent (inline) — override built-ins or define agents inline in
opencode.jsonc:"agent": { "build": { "model": "…", "mode": "subagent" } }. Inline keys override file-basedagents/<name>.md. - compaction —
{ "auto": bool, "prune": bool, "reserved": number }(defaults:autotrue,prunefalse).reservedis the token buffer kept to avoid overflow during compaction. - Environment escape hatches —
OPENCODE_CONFIG_DIRpoints at a custom config dir (searched like.opencode, loaded after it so it overrides);OPENCODE_CONFIGpoints at a single custom config file (loaded between global and project).
Agent frontmatter (agents/<name>.md)
| Key | Convention |
|---|---|
name |
kebab-case, matches filename |
description |
When to use this agent (drives routing + @-menu) |
mode |
primary | subagent |
model |
deepseek/deepseek-v4-pro | deepseek/deepseek-v4-flash | deepseek/deepseek-v4-flash-vision-exp (visual only) |
steps |
step budget; heavier agents get more |
color |
"#RRGGBB" |
hidden |
optional: hide from @-menu |
permission |
optional tool locks; read-only agents (oracle, reviewer, explore, librarian) must set edit: deny + read-only bash whitelist |
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.
- today Changed fed94c1a750d
- 4d ago First seen · 72 lines · 76 tokens per session scan C 9883e79b060a
opencode-config is a skill published in the GitHub repository znlgis/my-opencode-deepseek-config (57 stars, last pushed today), licensed MIT. It adds 76 tokens to every session and 1,195 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
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
微博内容创作 - 140字优化、话题热搜、@提及策略、配图描述、发布时机.
excel-helper
Excel 表格助手 - 公式编写、数据透视表、图表可视化、宏自动化、数据清洗.
code-mate-antigravity
Runs Antigravity CLI headlessly for repository analysis and coding tasks. Use when the user asks to delegate work to Antigravity CLI or compare its result with another coding agent.
code-mate-openclaw
Runs a local OpenClaw agent non-interactively and returns its structured response. Use when the user asks to delegate a bounded task to the OpenClaw main agent.
code-mate-qoder
Runs the Code Mate Qoder CN CLI non-interactively with structured output. Use when the user asks to delegate a bounded coding task to Qoder.