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/zekker6/devsandbox/devsandbox-confignpx skills add zekker6/devsandbox --skill devsandbox-configgit clone --depth 1 https://github.com/zekker6/devsandboxWhat 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 | $0.00208 | $0.02228 |
| Opus 5 | $0.00104 | $0.01114 |
| Sonnet 5 | $0.00042 | $0.00446 |
| Haiku 4.5 | $0.00021 | $0.00223 |
Grade A, and why
devsandbox-config 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 2d 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
devsandbox configuration
Answer configuration questions from the devsandbox documentation, fetched at the time you answer.
The one rule
Every section, key and value you name must come from a source you read in this session.
devsandbox ignores a key it does not recognize rather than rejecting it, so an invented key produces a config that looks applied and does nothing. A guess here is worse than no answer. If you cannot find a setting, say it does not exist and name where you looked. Never derive a key from a similar one - keep_container has no keep_containers, and [tools.git] taking mode does not mean [tools.docker] does.
If the documentation cannot be fetched, say so and stop. No network means no grounding, and answering from memory is the failure this skill exists to prevent. Offer the local alternatives below instead.
Sources, most authoritative first
-
A devsandbox checkout, if one is at hand. When the working directory is the devsandbox repository, read
docs/*.mddirectly - those match the code in front of you, andgrep -n 'toml:"' internal/config/config.golists every key of the fixed schema. Prefer this over fetching. -
The user's own machine, for anything that depends on their setup rather than on what the software supports:
devsandbox config path # where the global config lives devsandbox config show # the resolved configuration, after merging devsandbox doctor # installation, backend, firewall and config health devsandbox tools list # which tools are detected here devsandbox tools info <tool> # what a tool binds and what it accepts devsandbox filter show # active HTTP filter rules devsandbox trust list # directories whose .devsandbox.toml is trusted devsandbox --version # compare against the docs, see "Version skew" -
The published documentation, via
WebFetch. This is the normal path.
Fetching the documentation
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.
- 2d ago First seen · 109 lines · 208 tokens per session scan A c90dca54f0c0
devsandbox-config is a skill published in the GitHub repository zekker6/devsandbox (10 stars, last pushed 2d ago), licensed MIT. It adds 208 tokens to every session and 2,228 once invoked, about $0.0010 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 2026-08-31.
Other skills, from other repositories
cao-plugin
Create a new CAO (CLI Agent Orchestrator) plugin. Use this skill whenever the user wants to add a plugin that reacts to CAO lifecycle or messaging events, scaffold a plugin package, understand plugin requirements, or integrate an external system (Discord, Slack, dashboards, logging, metrics) with CAO. Also use when…
test-warp-ui
Guides testing Warp UI features and changes using the computer use tool. Use this skill only when computer-use testing was requested (explicit request or accepted offer) and the computeruse tool is available to the agent. Covers launching Warp and verifying UI behavior.
regex-mastery
Use this skill when writing regular expressions, debugging pattern matching,optimizing regex performance, or implementing text validation. Triggers on regex, regular expressions, pattern matching, lookahead, lookbehind, named groups, capture groups, backreferences, and any task requiring text pattern matching.
modify-settings
View or modify Warp application settings using the bundled JSON schema for guidance.
ws-ckpt
工作区快照管理。用户说"保存一下"、"存个快照"时创建 checkpoint，仅限 Linux; 说"回滚"、"撤销"、"恢复到之前"时 rollback;说"删掉快照"时 delete; 说"对比快照"、"快照改了什么"时 diff; 说"看看快照"、"有哪些快照"时 list;说"查看快照状态"、"查看快照剩余空间"时 status。.
host-pattern
Use when adding a new domain to Nuclear's plugin system, or implementing a host. Covers the host pattern (how player functionality is exposed to plugins), the host interface and API class structure, how hosts are implemented in the player, error handling conventions, and what files to create and modify. Trigger…