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-icp)<a href="https://agentmods.dev/commands/belkins/revenue-os/ros-icp"><img src="https://agentmods.dev/badge/commands/belkins/revenue-os/ros-icp/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-icp"><img src="https://agentmods.dev/badge/commands/belkins/revenue-os/ros-icp.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 | $0.00014 | $0.00939 |
| Opus 5 | $0.00007 | $0.00469 |
| Sonnet 5 | $0.00003 | $0.00188 |
| Haiku 4.5 | $0.00001 | $0.00094 |
Grade A, and why
ros-icp 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 — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ICP Finder
Arguments: $ARGUMENTS
Load Existing Data
!bash "${CLAUDE_PLUGIN_ROOT}/scripts/utils/storage.sh" read product
!bash "${CLAUDE_PLUGIN_ROOT}/scripts/utils/storage.sh" read icp
ICP Templates Reference
!cat "${CLAUDE_PLUGIN_ROOT}/data/icp-templates.json" 2>/dev/null || echo '{}'
Instructions
If $ARGUMENTS is empty or "discover":
FULL CODEBASE ANALYSIS MODE
-
Analyze the Project
- Use Glob to find: README.md, package.json, .config., main source files
- Use Read to examine key files
- Use Grep to search for keywords indicating purpose
-
Extract Product Intelligence
- What does this product do? (core function)
- What problem does it solve?
- What technologies does it use?
- Who would benefit from this?
-
Generate ICP Hypotheses
- Create 2-3 ICP hypotheses based on the product
- Use templates from icp-templates.json as starting points
- Customize based on what you discovered
-
Web Research
- Use WebSearch to find communities where these ICPs gather
- Search for: "[problem] forum", "[product type] community", "[industry] slack groups"
- Find validation signals (people complaining about the problem)
-
Output Complete ICP Profile
If $ARGUMENTS is "validate":
Use WebSearch to validate the existing ICP:
- Search for communities mentioned
- Look for discussions about the pain points
- Find competitor users complaining
- Verify budget expectations are realistic
If $ARGUMENTS is "refine":
Ask clarifying questions to improve the existing ICP.
If $ARGUMENTS is "find":
Use WebSearch to find actual potential customers:
- Search for job postings with relevant keywords
- Find company announcements related to the problem
- Look for social media posts expressing the pain point
If $ARGUMENTS is "personas":
Generate detailed buyer personas from the ICP with:
- Name, role, day-in-the-life
- Goals, frustrations, fears
- How they evaluate solutions
- Objections they'll raise
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 · 141 lines · 14 tokens per session scan A e14e421bfb84
ros-icp is a command published in the GitHub repository Belkins/revenue-os (29 stars, last pushed 1mo ago), licensed MIT. It adds 14 tokens to every session and 939 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.