Borrowing it
Nothing to install: this file belongs to cloudrepo-io/founder-os. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/cloudrepo-io/founder-os/master/.claude/commands/queue/revise.mdgit clone --depth 1 https://github.com/cloudrepo-io/founder-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/cloudrepo-io/founder-os/revise)<a href="https://agentmods.dev/commands/cloudrepo-io/founder-os/revise"><img src="https://agentmods.dev/badge/commands/cloudrepo-io/founder-os/revise.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 | $0.00006 | $0.00538 |
| Opus 5 | $0.00003 | $0.00269 |
| Sonnet 5 | $0.00001 | $0.00108 |
| Haiku 4.5 | $0.00001 | $0.00054 |
Grade A, and why
revise 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 8d 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Request Plan Revision
Request changes to a research plan that's in needs_review status. This creates a revision loop where the agent updates the plan based on feedback.
Arguments
$ARGUMENTS- (Optional) Task ID of the plan to revise. If not provided, show all plans awaiting review.
Process
-
Read
.claude/queue/backlog.jsonto find items withstatus: "needs_review" -
If no task ID provided:
- List all items with
needs_reviewstatus - Ask which plan to revise
- List all items with
-
If task ID provided (or after selection):
- Read the plan file at the item's
plan_filepath - Display the plan for context
- Read the plan file at the item's
-
Gather revision feedback:
Ask the user: "What changes do you want to the plan?"
Collect specific feedback. Good revision requests:
- "Consider approach X instead of Y"
- "The risk section doesn't address Z"
- "Split this into two phases"
- "Add more detail to the implementation steps"
- "What about impact on {system}?"
-
Update the research task:
{ "status": "pending", "revision_requested": true, "revision_count": {previous count + 1}, "revision_feedback": "Specific feedback from founder", "updated": "ISO timestamp" }Keep all other fields unchanged. The task stays in backlog with
pendingstatus so/queue:workwill pick it up again. -
Report:
- Revision requested for {task ID}
- Feedback recorded
- "The agent will pick this up on next
/queue:workand update the plan"
Revision Workflow
Plan created → needs_review → /queue:revise → pending (with feedback) → agent revises → needs_review → repeat or /queue:approve
How the Agent Handles Revisions
When /queue:work picks up a task with revision_requested: true:
- The agent reads the existing plan file
- Reads the
revision_feedback - Updates the plan to address the feedback
- Sets status back to
needs_review - Clears
revision_requested
This creates a natural review loop until the founder approves.
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.
- 8d ago First seen · 77 lines · 6 tokens per session scan A 885b184a3a7a
revise is a command published in the GitHub repository cloudrepo-io/founder-os (19 stars, last pushed 7mo ago), licensed MIT. It adds 6 tokens to every session and 538 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
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.