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 writing-for-agentsgit 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/writing-for-agents)<a href="https://agentmods.dev/skills/znlgis/my-opencode-deepseek-config/writing-for-agents"><img src="https://agentmods.dev/badge/skills/znlgis/my-opencode-deepseek-config/writing-for-agents/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/znlgis/my-opencode-deepseek-config/writing-for-agents"><img src="https://agentmods.dev/badge/skills/znlgis/my-opencode-deepseek-config/writing-for-agents.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 | $0.00066 | $0.01116 |
| Opus 5 | $0.00033 | $0.00558 |
| Sonnet 5 | $0.00013 | $0.00223 |
| Haiku 4.5 | $0.00007 | $0.00112 |
Grade A, and why
writing-for-agents 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 10d 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Writing For Agents
Packaging differs; the writing levers are the same: make the agent take the same process every run, not the same output.
Context pointers
A context pointer names out-of-context material and encodes when to reach
it: a skill's description, a line in AGENTS.md pointing at a doc. Its wording,
not its target, decides when the agent reaches the material. A must-have target
behind a weak pointer is a variance bug: sharpen the wording first, inline only
if sharpening fails.
A pointer does two jobs — say what the material is, and list the branches (distinct cases the doc handles) that trigger reaching it. Every word of an always-loaded pointer costs on every turn, so prune it hardest:
- Front-load the leading word — that's where it fires.
- One trigger per branch — synonyms are one branch written twice; collapse them.
- Cut identity the body already carries.
The two loads
Every doc and pointer spends one of two budgets:
- Context load — always-loaded material (an
AGENTS.mdline, a skill description) costing tokens every turn whether or not it fires. - Cognitive load — the human remembering which docs exist and when to reach for each. Not a cost to minimise: it's the price of human agency. Spend it where judgement matters, remove it where it doesn't.
Information hierarchy
Rank content by how immediately the agent needs it:
- In-file step — ordered actions, the primary tier.
- In-file reference — definitions and rules consulted on demand.
- Disclosed reference — pushed to a separate file, reached by a pointer.
Progressive disclosure moves material down the ladder so the top stays legible. Branching is the cleanest test: inline what every branch needs; push behind a pointer what only some branches reach. Co-location keeps a concept's definition, rules, and caveats under one heading. Sprawl is the failure mode: disclose reference and split by branch or sequence.
Steps and completion criteria
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.
- 10d ago First seen · 98 lines · 66 tokens per session scan A 6abebdca86aa
writing-for-agents is a skill published in the GitHub repository znlgis/my-opencode-deepseek-config (58 stars, last pushed yesterday), licensed MIT. It adds 66 tokens to every session and 1,116 once invoked, about $0.0003 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
my-opencode-deepseek-config
Use when deploying, tuning, or extending the OpenCode × DeepSeek V4 optimal configuration (orchestrator routing, 12 agents, thinking tiers, prompt-cache prefix discipline, DCP compaction, permissions baseline, 25 skills, slash commands) — installing to another machine, adding an agent or skill, adjusting model…
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.