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 tallesborges/zdx --skill automationsgit clone --depth 1 https://github.com/tallesborges/zdxWrote 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/tallesborges/zdx/automations)<a href="https://agentmods.dev/skills/tallesborges/zdx/automations"><img src="https://agentmods.dev/badge/skills/tallesborges/zdx/automations.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 8 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00051 | $0.01949 |
| Opus 5 | $0.00026 | $0.00975 |
| Sonnet 5 | $0.00010 | $0.00390 |
| Haiku 4.5 | $0.00005 | $0.00195 |
Grade A, and why
automations 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 7d 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 — 209 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Automations Skill
Create and maintain ZDX automation files.
What is an Automation?
An automation is a headless agent that runs unattended — no human in the loop. It always produces a visible effect (a report, a message, a file, a PR). It must handle errors on its own: retry, degrade gracefully, or report what failed. Every automation is a single markdown file with YAML frontmatter and a prompt body.
Contract (must follow)
- Keep automations global-only in
$ZDX_HOME/automations/(usually$HOME/.zdx/automations/). - Treat one file as one automation.
- Derive automation identity from file stem (no
idfield).- Example:
~/.zdx/automations/morning-report.md→morning-report.
- Example:
- Require markdown with YAML frontmatter delimited by
---. - Keep prompt body as non-empty markdown after frontmatter.
Allowed frontmatter keys
schedule(string, optional cron)model(string, optional)timeout_secs(int, optional, must be> 0)max_retries(int, optional, default0)
Do not add extra keys unless explicitly requested.
Design Principles
Keep prompts concise
Include only the instructions needed to execute the task.
Keep prompts deterministic
Use explicit expected output shape (sections/bullets/constraints) so runs are easy to review.
Keep scope tight
Only modify automation files and only the fields needed for the request.
Always deliver a visible result
Every run must produce something the user can see — a thread entry, a message, a file. If the main output fails, produce a degraded result that explains what happened.
Handle the empty state
Prompts must say what to do when there's nothing to report (e.g., "If no PRs are open, return: No open PRs today."). Never produce a blank run.
Chain skills for delivery
When external delivery is needed, reference specific skills/tools (e.g., gog for email, wacli for WhatsApp). Don't reinvent what a skill already does.
Prefer staged execution over monolithic scripts
When prompt instructions involve external systems, prefer staged steps with clear checkpoints and fallback behavior.
What ships with it
3 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.
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.
- 7d ago First seen · 209 lines · 51 tokens per session scan A 504dc34e2294
automations is a skill published in the GitHub repository tallesborges/zdx (20 stars, last pushed 3d ago), licensed MIT. It adds 51 tokens to every session and 1,949 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…