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 codemapgit 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/codemap)<a href="https://agentmods.dev/skills/znlgis/my-opencode-deepseek-config/codemap"><img src="https://agentmods.dev/badge/skills/znlgis/my-opencode-deepseek-config/codemap/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/codemap"><img src="https://agentmods.dev/badge/skills/znlgis/my-opencode-deepseek-config/codemap.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 | $0.00067 | $0.00933 |
| Opus 5.5 | $0.00027 | $0.00373 |
| Sonnet 5.5 | $0.00013 | $0.00187 |
| Haiku 4.5 | $0.00007 | $0.00093 |
Grade A, and why
codemap 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codemap
Generate a compact, annotated directory tree that helps any agent quickly understand what a codebase contains and where key things live. One well-crafted codemap can replace dozens of exploratory globs and reads across a session.
When to use me
- First time entering a new repository or unfamiliar subdirectory
- The user asks "what's in this project?" or "show me the project structure"
- You need to understand the lay of the land before deciding where to search
- An agent keeps globbing the same directories — a codemap saves those tokens
How to generate
Step 1: Build the raw tree
Use the appropriate file listing for the platform:
# Windows (PowerShell)
Get-ChildItem -Recurse -Depth 3 -Name | Where-Object { $_ -notmatch 'node_modules|\.git|dist|build|\.next|coverage|__pycache__|\.venv' }
# Unix
find . -maxdepth 3 -not -path '*/node_modules/*' -not -path '*/.git/*' -not -path '*/dist/*' -not -path '*/build/*' | sort
Adjust the depth and exclusions based on repo size. For very large repos, start at depth 2 and expand specific directories on demand.
Step 2: Annotate the tree
After generating the raw tree, annotate key directories with one-line purpose descriptions. Only annotate directories whose purpose isn't obvious from the name.
project-root/
├── src/ # main source
│ ├── app/ # Next.js App Router pages + layouts
│ ├── components/ # shared React components
│ ├── lib/ # utilities, API clients, shared logic
│ └── server/ # server-only code (DB, auth)
├── prisma/
│ └── schema.prisma # database schema
├── public/ # static assets
├── tests/ # integration + e2e tests
├── package.json # Node dependencies + scripts
└── tsconfig.json # TypeScript config
Step 3: Add quick-reference metadata
At the bottom, add a few lines that capture the project's essence:
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 · 102 lines · 67 tokens per session scan A 00bee4ea0854
codemap is a skill published in the GitHub repository znlgis/my-opencode-deepseek-config (59 stars, last pushed yesterday), licensed MIT. It adds 67 tokens to every session and 933 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
orca-cli
Operate Orca-managed worktrees, folder contexts, terminals, repos, automations, artifacts, skill sharing, worktree comments, and Orca's embedded browser through the orca CLI. Use when the user says "$orca-cli", "Orca worktree", "child worktree", "spawn codex/claude in a worktree", "read/wait/send Orca terminal"…
refit
Cross-session environment retrospective driven by OMC's own instrumentation — trace timelines, friction reports, logs, and plan notepads. Every finding lands on the surface that owns the fix (deterministic check, steering volume, tooling, or information access); nothing is written without user approval.
minimal-code-discipline
YAGNI-ladder coding discipline for writing changes — existence-first, reuse before writing, dependency ladder, shortest correct diff, with non-negotiables that must never be minimized away.
claude-automation-recommender
Recommend Claude Code automations (hooks, subagents, skills, plugins, MCP) and review an existing setup.
cherry-computer
Drive native apps via Computer Use: open, inspect, type, click, screenshot. Needs OS permissions; respect user stop.
skills-manager
A tool for finding, installing, and coordinating Claude Code Agent Skills. These skills are reusable instructions that add specific abilities to Claude Code.