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 jvPalma/dotrun --skill dr-cligit clone --depth 1 https://github.com/jvPalma/dotrunWrote 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/jvpalma/dotrun/dr-cli)<a href="https://agentmods.dev/skills/jvpalma/dotrun/dr-cli"><img src="https://agentmods.dev/badge/skills/jvpalma/dotrun/dr-cli/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/jvpalma/dotrun/dr-cli"><img src="https://agentmods.dev/badge/skills/jvpalma/dotrun/dr-cli.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00017 | $0.02827 |
| Opus 5.5 | $0.00007 | $0.01131 |
| Sonnet 5.5 | $0.00003 | $0.00565 |
| Haiku 4.5 | $0.00002 | $0.00283 |
Grade A, and why
dr-cli 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 — 317 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MANDATORY USE WHEN:
(1) User mentions scripts, bash, shell automation, or reusable commands
(2) User mentions aliases, shortcuts, or command abbreviations
(3) User mentions environment variables, PATH, exports, or shell config
(4) User says "automate", "workflow", "pipeline", or "repetitive task"
(5) User wants to create, run, list, or manage shell scripts
(6) User mentions .bashrc, .zshrc, config.fish, or dotfiles migration
(7) AI needs to automate a task that will be needed again - ALWAYS prefer dr scripts
Decision Routing Matrix
CRITICAL: Route ALL shell automation through dr.
for just folders and filenames: dr -l, for folders + filenames + 1 line description dr -L
Use this matrix:
| User Intent | dr Command | Check First |
|---|---|---|
| Create/run bash script | dr set <name> / dr <name> |
dr -l/L |
| Shell alias/shortcut | dr -a <name> |
dr -a -l/L |
| Environment variable/PATH | dr -c <name> |
dr -c -l/L |
| Migrate shell config | See migration refs | - |
| Repetitive workflow | dr set <category>/<name> |
dr -l/L |
Trigger Detection
User says "script", "bash", "automate" → dr set <name>
User says "alias", "shortcut" → dr -a <name>
User says "export", "PATH", "env var" → dr -c <name>
User says "migrate file" + path → Load migration-workflow.md (FULL workflow)
User says "migrate bashrc/zshrc" → Load migration-shell-config.md
User says "import scripts from ~/bin" → Load migration-scripts.md
User does same task twice → Proactively suggest dr script
Discovery Before Creation (MANDATORY)
NEVER create a script without checking first:
# Step 1: ALWAYS run this first
dr -l/L # List ALL scripts with descriptions
# Step 2: Narrow search if needed
dr -l/L <folder>/ # e.g., dr -L git/
dr help <script-name> # Verify script purpose
What ships with it
12 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- .cursorrules 1.5 KB
- AGENTS.md 3.2 KB
- copilot-instructions.md 2.0 KB
- README.md 3.4 KB
- references/architecture.md 3.6 KB
- references/commands.md 3.3 KB
- references/developer-prompts.md 2.6 KB
- references/migration-formats.md 3.3 KB
- references/migration-helpers.md 3.5 KB
- references/migration-scripts.md 4.0 KB
- references/migration-shell-config.md 3.5 KB
- references/migration-workflow.md 19 KB
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 · 317 lines · 17 tokens per session scan A f0a86a1ccd0c
dr-cli is a skill published in the GitHub repository jvPalma/dotrun (10 stars, last pushed 7mo ago), licensed MIT. It adds 17 tokens to every session and 2,827 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
arkcli-models
A catalogue and lookup tool for ARK AI models, including their versions, supported input types, context limits, and lifecycle status. It can also list models belonging to your account.
arkcli-doctor
A diagnostic tool for ARK services, accounts, models, and inference endpoints. An inference endpoint is the online address through which an AI model receives requests.
arkcli-gen
An ArkCLI workflow for generating images and videos with Ark models. Image results return immediately, while video generation runs as a background job that must be checked until finished.
arkcli-plans
A subscription manager for ARK Agent Plans and Coding Plans, including personal and team subscriptions. It also manages team seats, which are assigned places for employees, and their API keys.
arkcli-docs
A reader for official Ark documentation, including pages, API descriptions, and required request fields. Ark is a cloud platform, and this add-on uses its official documentation as the source of truth.
arkcli-deploy
A deployment workflow for creating an online inference endpoint from an AI model. Creating one is a real account change that can create a billable resource.