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 cosmicstack-labs/mercury-agent-skills --skill workflow-automationgit clone --depth 1 https://github.com/cosmicstack-labs/mercury-agent-skillsWrote 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/cosmicstack-labs/mercury-agent-skills/workflow-automation)<a href="https://agentmods.dev/skills/cosmicstack-labs/mercury-agent-skills/workflow-automation"><img src="https://agentmods.dev/badge/skills/cosmicstack-labs/mercury-agent-skills/workflow-automation/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/cosmicstack-labs/mercury-agent-skills/workflow-automation"><img src="https://agentmods.dev/badge/skills/cosmicstack-labs/mercury-agent-skills/workflow-automation.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 | $0.00025 | $0.04270 |
| Opus 5 | $0.00013 | $0.02135 |
| Sonnet 5 | $0.00005 | $0.00854 |
| Haiku 4.5 | $0.00003 | $0.00427 |
Grade A, and why
Workflow Automation 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 — 568 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Workflow Automation
Core Principles
1. Reliability First
Every workflow must handle failure gracefully. Automations should degrade predictably, not silently. A workflow that fails noisily is better than one that fails silently — at least you know to fix it.
2. Idempotency
Design every action to be safe to run multiple times. If a workflow retries mid-way, running the same step twice should produce the same result as running it once. This is the single most important property for building reliable automations.
3. Observability
You cannot improve what you cannot see. Every workflow must log key events, expose execution traces, and alert on failures. Treat your workflows as production systems — because they are.
4. Loose Coupling
Workflow steps should communicate through well-defined interfaces (files, databases, APIs), not through shared mutable state. This allows steps to be replaced, tested, and scaled independently.
5. Fail Fast, Recover Gracefully
Validate inputs immediately at the start of a workflow. Catch known error conditions early. For unexpected errors, have a fallback path — don't let a single failure cascade through the entire system.
Automation Maturity Model
| Level | Name | Description |
|---|---|---|
| 0 | Ad-hoc | Manual processes, no automation. Everything done by hand. |
| 1 | Basic | Simple single-step automations. No error handling. Manual retries. |
| 2 | Structured | Multi-step workflows with basic error handling. Logs exist but aren't monitored. |
| 3 | Reliable | Idempotent steps, retry with backoff, dead letter queues. Alerts on failure. |
| 4 | Observable | Full execution tracing, dashboards, performance metrics. Proactive alerting. |
| 5 | Self-healing | Automatic rollback, compensating transactions, adaptive error handling. |
Target at least Level 3 for any workflow that touches production data.
Workflow Design Patterns
Triggers → Actions → Error Handling
Every workflow follows a three-phase structure:
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 · 568 lines · 25 tokens per session scan A 1164c8edbb45
Workflow Automation is a skill published in the GitHub repository cosmicstack-labs/mercury-agent-skills (470 stars, last pushed 15d ago), licensed MIT. It adds 25 tokens to every session and 4,270 once invoked, about $0.0001 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
stay-within-limits
Use when long-running or parallel agent work must respect 5-hour and weekly usage limits by checking usage between waves, pausing near the cap, and resuming only when the window is clear.
obsidian-bases
Create and edit Obsidian Bases (.base files) with views, filters, formulas, and summaries. Use when working with .base files, creating database-like views of notes, or when the user mentions Bases, table views, card views, filters, or formulas in Obsidian.
find-journalists
Build, refine, dedupe, and enrich small fit-checked journalist lists for newsjack campaigns. Uses the newsjack CLI (preferred) or the medialyst MCP for news search and journalist enrichment, and falls back to a best-effort local mode with no verified contacts; the agent owns how returned data is organized.
story-origin-check
Recover the first public timestamp and canonical major coverage for a newsjacking signal, then decide whether newer coverage is the same story, a different story, or a materially new development.
agent-estate
Perpetual autonomous work loop for Claude Code — no end condition, no memory regression, no context overfill. Maintains a persistent ledger across all sessions.
prompt-proximity-architecture
Turn an approved measurement charter, ICPs, and buyer jobs into a budget-aware prompt coverage blueprint across proximity bands, aided status, information acts, journey states, roles, locales, evidence grades, partitions, and measurement lanes. Use before prompt wording to define required, optional, and prohibited…