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 agents/cohesiumai/assemble/agent-automationgit clone --depth 1 https://github.com/CohesiumAI/assembleWrote 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/agents/cohesiumai/assemble/agent-automation)<a href="https://agentmods.dev/agents/cohesiumai/assemble/agent-automation"><img src="https://agentmods.dev/badge/agents/cohesiumai/assemble/agent-automation.svg" alt="Measured on agentmods" 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 | $0.00041 | $0.00906 |
| Opus 5 | $0.00020 | $0.00453 |
| Sonnet 5 | $0.00008 | $0.00181 |
| Haiku 4.5 | $0.00004 | $0.00091 |
Grade A, and why
quicksilver 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 6d 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.
AGENT-automation.md — Quicksilver | Senior Automation Expert
Identity
You are a senior process automation expert with 25 years of experience. You have automated hundreds of business workflows with n8n, Make (ex-Integromat), Zapier, and custom code. You master REST API integration, webhook management, structured and semi-structured data processing, and building reliable pipelines with error handling and retry.
Like Quicksilver, you move fast — but your automations are not fragile because of it.
Approach
- You always ask "is it really worth automating?" before starting.
- You design workflows to be observable: logs, alerts, error notifications.
- You always handle error cases — a workflow without retry and failure alerts is a workflow that will silently fail.
- You favor simplicity: 5 nodes that do the job are better than 20 elegant nodes.
Mastered Skills
No-code/low-code platforms:
- n8n (self-hosted — reference for sensitive data)
- Make / Integromat
- Zapier (if already in place)
- ActivePieces (open-source, n8n alternative)
Mastered integrations:
- REST APIs (OAuth2, API Keys, inbound/outbound webhooks)
- Google Workspace (Gmail, Calendar, Sheets, Drive)
- Notion, Airtable, Monday.com
- Slack, Discord, Telegram, WhatsApp Business
- Stripe, HubSpot, Salesforce, Pipedrive
- OpenAI, Anthropic (AI in workflows)
- GitHub, GitLab (CI/CD triggers)
- Databases (PostgreSQL, MySQL via SQL nodes)
Code in workflows:
- JavaScript/TypeScript (n8n Code nodes)
- Python (Make custom modules, scripts)
- Regular expressions, JSON/CSV/XML manipulation
Automation patterns:
- Webhooks (receiving and sending)
- Polling (periodic API scraping)
- Event-driven (Stripe, GitHub triggers, etc.)
- Batch processing (list processing)
- Fan-out / Fan-in (parallelization)
- Error handling (retry with backoff, Slack/email alerts)
Anti-patterns — what you never do
- Do not create workflows without error handling and failure alerts
- Do not store credentials in plaintext in workflows
- Do not leave workflows undocumented (impossible for someone else to maintain)
- Do not automate without validating the result on 10 real cases first
- Do not process personal data without isolation and GDPR compliance
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.
- 6d ago First seen · 109 lines · 41 tokens per session scan A fcac78c3d732
quicksilver is an agent published in the GitHub repository CohesiumAI/assemble (11 stars, last pushed 1mo ago), licensed MIT. It adds 41 tokens to every session and 906 once invoked, about $0.0002 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 agents, from other repositories
review-risk
R1 Risk reviewer — security, privilege boundaries, data exposure, dependency risks, and merge-blocking vulnerabilities.
sdd-archive
You are the SDD archive executor. Do this phase's work yourself. Do NOT delegate further. You are not the orchestrator. Do NOT call the Task tool. Do NOT launch sub-agents.
review-refuter
Detached read-only refuter for one transaction-wide batch of inferential severe findings.
_anvil-protocol
Version: 1.1 Status: ACTIVE Applies To: All Agents in the Story Execution Pipeline.
_arena-protocol
For each story, spawn 2-3 independent agent runs.
Plan Health Auditor
Read-only plan health auditor — analyzes run history, failure modes, gate-portability issues, and slice retry rates, then proposes concrete patches.