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.
git clone --depth 1 https://github.com/Workflowsio/company-os-starter-kitWrote 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/commands/workflowsio/company-os-starter-kit/compound)<a href="https://agentmods.dev/commands/workflowsio/company-os-starter-kit/compound"><img src="https://agentmods.dev/badge/commands/workflowsio/company-os-starter-kit/compound/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/commands/workflowsio/company-os-starter-kit/compound"><img src="https://agentmods.dev/badge/commands/workflowsio/company-os-starter-kit/compound.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 | $0.00021 | $0.01770 |
| Opus 5.5 | $0.00008 | $0.00708 |
| Sonnet 5.5 | $0.00004 | $0.00354 |
| Haiku 4.5 | $0.00002 | $0.00177 |
Grade A, and why
workflows:compound 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 yesterday.
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 — 227 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/compound
Coordinate multiple subagents working in parallel to document a recent win, process improvement, or playbook discovery.
This command references the compound-docs and setup skills, which this kit does not ship. If a skill is not installed, follow this file's own inline instructions for that step and say in the run summary that you did.
Purpose
Captures what worked while context is fresh, creating structured documentation in docs/wins/ with YAML frontmatter for searchability and future reference. Uses parallel subagents for maximum efficiency.
Why "compound"? Each documented win compounds your team's knowledge. The first time you crack a new campaign angle takes weeks of testing. Document it, and the next client gets that playbook on day one. Knowledge compounds.
Usage
/workflows:compound # Document the most recent win
/workflows:compound [brief context] # Provide additional context hint
Execution Strategy: Two-Phase Orchestration
<critical_requirement> Only ONE file gets written - the final documentation.
Phase 1 subagents return TEXT DATA to the orchestrator. They must NOT use Write, Edit, or create any files. Only the orchestrator (Phase 2) writes the final documentation file. </critical_requirement>
Phase 1: Parallel Research
<parallel_tasks>
Launch these subagents IN PARALLEL. Each returns text data to the orchestrator.
1. Context Analyzer
- Extracts conversation history and relevant data
- Identifies win type, client/campaign, channel, metrics
- Validates against schema
- Returns: YAML frontmatter skeleton
2. Win Extractor
- Analyzes what was tried and what actually worked
- Identifies the specific tactic, angle, or process change
- Extracts results with real numbers where available
- Returns: Win content block
3. Related Docs Finder
- Searches
docs/wins/for related documentation - Identifies cross-references and links
- Finds related client work or campaigns
- Returns: Links and relationships
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.
- yesterday First seen · 227 lines · 21 tokens per session scan A 97825b5f0c35
workflows:compound is a command published in the GitHub repository Workflowsio/company-os-starter-kit (104 stars, last pushed yesterday), licensed MIT. It adds 21 tokens to every session and 1,770 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 2026-11-09.
workflows:compound compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| workflows:compoundWorkflowsio/company-os-starter-kit | Command | 104 | yesterday | MIT | A | 21 | Claude Code |
| _registry-protocolChappygo-OS/Atomic-Spec | Command | 10 | 4d ago | MIT | A | 0 | Claude Code |
| mach12:gh-pr-readLeanAndMean/scramjet | Command | 8 | 8d ago | Apache-2.0 | A | 25 | Claude Code |
| scramjet:troubleshootLeanAndMean/scramjet | Command | 8 | 8d ago | Apache-2.0 | A | 9 | Claude Code |
| gaai-auditdigipulse-engineering/GAAI-framework | Command | 163 | 8d ago | none | A | 10 | Claude Code |
| cold-startkunalsuri/ai-fication-kit | Command | 3 | 26d ago | Apache-2.0 | A | 28 | GitHub Copilot |
| healthalexgreensh/token-optimizer | Command | 2.9k | yesterday | none | C | 28 | Claude Code |