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-outreach)<a href="https://agentmods.dev/commands/belkins/revenue-os/ros-outreach"><img src="https://agentmods.dev/badge/commands/belkins/revenue-os/ros-outreach/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-outreach"><img src="https://agentmods.dev/badge/commands/belkins/revenue-os/ros-outreach.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 | $0.00007 | $0.00702 |
| Opus 5 | $0.00003 | $0.00351 |
| Sonnet 5 | $0.00001 | $0.00140 |
| Haiku 4.5 | $0.00001 | $0.00070 |
Grade A, and why
ros-outreach 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 11d 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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Outreach Generator
Arguments: $ARGUMENTS
Load Data
!bash "${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
!cat "${CLAUDE_PLUGIN_ROOT}/data/outreach-templates.json" 2>/dev/null
Instructions
Prerequisites Check
- If no ICP defined, prompt user to run /revenue-os:ros-icp first
- If no value prop defined, prompt user to run /revenue-os:ros-value-prop first
If $ARGUMENTS is empty or "cold-email":
Generate a 4-email cold outreach sequence:
- Use ICP data to understand the target
- Use value prop for messaging
- Apply templates but customize for specific product/audience
- Include personalization variables
If $ARGUMENTS is "linkedin":
Generate LinkedIn outreach:
- Connection request (under 300 chars)
- First message after accept
- Follow-up pitch message
If $ARGUMENTS is "twitter":
Generate Twitter/X DM sequence.
If $ARGUMENTS is "follow-up":
Generate follow-up sequences for warm leads.
If $ARGUMENTS contains "for":
Personalize for specific target company:
- WebSearch for company info, recent news
- Find decision maker info
- Customize outreach with specific details
Output Format
## Cold Email Sequence: [ICP Name]
### Sequence Overview
- 4 emails over 14 days
- Expected response rate: 5-15%
- Best send times: Tuesday-Thursday, 9-11am
---
### Email 1: The Pattern Interrupt
**Day 1 | Subject**: [Subject line]
Hi {{first_name}},
[Body using ICP pain points and value prop]
[Your name]
---
### Email 2: The Value Bomb
**Day 3 | Subject**: Re: [previous]
{{first_name}},
[Pure value content]
---
### Email 3: The Social Proof
**Day 7 | Subject**: [Social proof subject]
{{first_name}},
[Case study + soft CTA]
---
### Email 4: The Breakup
**Day 14 | Subject**: Closing the loop
{{first_name}},
[Final CTA + door open]
---
### Personalization Guide
- {{first_name}} - First name
- {{company}} - Company name
- {{specific_pain}} - Their specific pain point
- {{recent_news}} - Recent company news to reference
### Tips for Success
1. [Tip 1]
2. [Tip 2]
3. [Tip 3]
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.
- 11d ago First seen · 118 lines · 7 tokens per session scan A 6cb02f75dcbb
ros-outreach is a command published in the GitHub repository Belkins/revenue-os (29 stars, last pushed 1mo ago), licensed MIT. It adds 7 tokens to every session and 702 once invoked, about $0.0000 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.