Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add Belkins/revenue-os/plugin install revenue-osWrote 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/belkins/revenue-os/ros-value-prop)<a href="https://agentmods.dev/commands/belkins/revenue-os/ros-value-prop"><img src="https://agentmods.dev/badge/commands/belkins/revenue-os/ros-value-prop/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/belkins/revenue-os/ros-value-prop"><img src="https://agentmods.dev/badge/commands/belkins/revenue-os/ros-value-prop.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 | $0.00013 | $0.01002 |
| Opus 5 | $0.00006 | $0.00501 |
| Sonnet 5 | $0.00003 | $0.00200 |
| Haiku 4.5 | $0.00001 | $0.00100 |
Grade A, and why
ros-value-prop 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 12d 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 — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Value Proposition Polisher
Arguments: $ARGUMENTS
Load Existing Data
!bash "${CLAUDE_PLUGIN_ROOT}/scripts/utils/storage.sh" read product
!bash "${CLAUDE_PLUGIN_ROOT}/scripts/utils/storage.sh" read icp
!bash "${CLAUDE_PLUGIN_ROOT}/scripts/utils/storage.sh" read value-prop
Frameworks Reference
!cat "${CLAUDE_PLUGIN_ROOT}/data/value-prop-frameworks.json" 2>/dev/null || echo '{}'
Instructions
If $ARGUMENTS is empty or "generate":
-
Load Context
- Read ICP from saved data (or ask user to run /revenue-os:ros-icp first)
- Analyze product from codebase if not already done
-
Research Competitors (WebSearch)
- Search for competitor positioning
- Note their headlines, value props
- Identify gaps in their messaging
-
Generate Value Propositions
- Apply each framework to create options
- Focus on ICP's specific pain points
- Differentiate from competitors
-
Polish and Output
- Provide headline, subheadline, one-liner
- Multiple positioning angles for A/B testing
- Ready-to-use copy snippets
If $ARGUMENTS is "analyze":
Analyze existing positioning (README, website if provided):
- Identify current messaging
- Highlight weak points
- Suggest improvements
If $ARGUMENTS is "test":
Generate 3-4 variant headlines/value props for A/B testing.
If $ARGUMENTS contains "framework":
Use the specified framework exclusively.
If $ARGUMENTS contains "for":
Tailor specifically for the named ICP segment.
Output Format
## Value Proposition: [Product Name]
### For: [ICP Name]
---
### Product Understanding
- **What it does**: [core function]
- **Key differentiator**: [unique aspect]
- **Alternatives**: [what people use instead]
---
### The Winning Value Proposition
**Headline** (8 words max)
> [Compelling headline]
**Subheadline** (20 words max)
> [Clarification of what, for whom, why it matters]
**One-Liner** (for bios, tweets, conversations)
> "[Product] helps [ICP] [achieve outcome] without [pain point]."
---
### The 3 Key Benefits
1. **[Benefit 1]**
- Feature: [underlying feature]
- So what: [why it matters]
- Proof: [how to prove it]
2. **[Benefit 2]**
- Feature: [underlying feature]
- So what: [why it matters]
- Proof: [how to prove it]
3. **[Benefit 3]**
- Feature: [underlying feature]
- So what: [why it matters]
- Proof: [how to prove it]
---
### Positioning Angles (A/B Test These)
**Angle A: Pain-Killer**
> "[Pain-focused headline]"
Best for: Frustrated audiences seeking relief
**Angle B: Gain-Creator**
> "[Gain-focused headline]"
Best for: Ambitious audiences seeking growth
**Angle C: Competitive**
> "[Differentiation headline]"
Best for: Audiences comparing alternatives
**Angle D: Social Proof**
> "[Social proof headline]"
Best for: Risk-averse audiences
---
### Elevator Pitch (30 seconds)
"You know how [ICP] struggle with [problem]? They usually [current solution] which [limitation].
[Product] is a [category] that [key differentiator]. Unlike [alternative], we [unique mechanism].
Our users [specific outcome with metric]."
---
### Ready-to-Use Copy
**Hero Section**
[Headline]
[Subheadline]
[CTA button text]
**Email Subject Lines**
1. [Option 1]
2. [Option 2]
3. [Option 3]
**Tweet**
[Ready-to-post tweet]
**LinkedIn Post**
[Ready-to-post LinkedIn content]
---
### Next Steps
1. A/B test headlines with `/revenue-os:ros-landing-page`
2. Create outreach using this messaging with `/revenue-os:ros-outreach`
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.
- 12d ago First seen · 170 lines · 13 tokens per session scan A 0b7db654f671
ros-value-prop is a command published in the GitHub repository Belkins/revenue-os (29 stars, last pushed 1mo ago), licensed MIT. It adds 13 tokens to every session and 1,002 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 commands, from other repositories
maintain
Run automated maintenance — seeker finds bugs from pod logs and raises GitHub issues, fixer picks them up and creates PRs. Can run as a one-shot or scheduled via /schedule.
save
Save current work state for next session. Creates/updates .planning/ files (CHECKPOINT.md, STATE.md, settings.json) so Heimdall resumes with full context. NOT a rewind — saves forward progress. Run before closing a session or at any milestone.
plan-review
Multi-model plan review — AI models independently plan, then converge on the best approach.
review
Multi-model review — AI models independently review any document or general topic, then converge on findings.
code-review
Multi-model code review — AI models independently review code, then converge on findings.
autonomy
Set Heimdall autonomy (1=Guided, 2=Checkpoint, 3=Full Auto) — how much the agent does before asking. Use with a number, +/- to cycle, or no argument to show current.