permissions
Skill0 starsChanged 5 months agoMITView on GitHub
Permissions and kill-switch. Use when the operator says "permissions", "authority", "tier", "kill switch", "stop", "shut it down", "pause", "raise tier", "lower tier", or any time the system is about to perform an action with real-world consequences (sending email, posting listing, committing money). Defines and enforces the authority tier the coordinator and all sub-agents operate under.
4 other projects use a version of this.
Adopted by
Most recently taken up by
- reisi007/agents-skillstheir own version, first seen Nov 5, 2026
- pantalytics/odoo-mcp-protheir own version, first seen Oct 12, 2026
- oprogramadorreal/optimus-claudetheir own version, first seen Sep 4, 2026
- aborroy/aiup-alfrescotheir own version, first seen Jun 22, 2026
Other versions4 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 4
- pantalytics/odoo-mcp-pro★ 91same name
- oprogramadorreal/optimus-claude★ 75same name
- aborroy/aiup-alfresco★ 14same name
- reisi007/agents-skills★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository9 other files it gives its agents.
- coordinatorSkill
- decision-queueSkill
- discovery-sprintSkill
- hair-productSkill
- midday-pulseSkill
- morning-briefSkill
- nightly-wrapSkill
- revenue-experimentSkill
- venture-triageSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
20 rules. 0 are common, 17 are distinctive, and 3 are very specific to this project.
0
Common
Most of the 3 edited versions we read keep these.
17
Distinctive
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 50
No spending >$50 in a single action without the operator's explicit per-action approval
- Distinctive: line 51
No trading. the operator trading restrictions apply and the system has no broker access.
- Distinctive: line 53
No posting to public social media on the operator's personal accounts.
- Distinctive: line 54
No a partner-related actions (her platform, their work) without her explicit OK.
- Distinctive: line 60
When the operator says "raise to tier 2" or similar:
- Distinctive: line 62
Verify the tier change is intentional.
- Distinctive: line 63
If raising to Tier 3, list the auto-rules currently configured and confirm.
- Very specific: line 64
Update permissions.md. Log the change with timestamp and reason.
- Distinctive: line 69
When the operator says "stop", "kill", "shut it down", "emergency":
- Distinctive: line 73
Write the kill event to the audit log.
- Distinctive: line 74
Ask the operator what triggered the kill so the lesson is captured.
- Very specific: line 78
Before any sub-agent or skill takes an external action, it must consult permissions.md:
- Distinctive: line 81
Check if action is allowed at this tier.
- Distinctive: line 82
If not allowed, refuse and propose what tier would be needed.
- Distinctive: line 83
If allowed, perform action and log to audit.
- Very specific: line 87
When nightly-wrap runs and the operator will be away for 8+ hours:
- Distinctive: line 89
If tier is 2 or 3, default-recommend dropping to 1.
- Distinctive: line 90
If the operator explicitly wants to maintain tier overnight, log the override with reason.
- Distinctive: line 118
Tier never auto-raises: Only the operator raises.
- Distinctive: line 120
Audit log is append-only: Never edit history.
“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Permissions
The blast-radius controller for vantage-os.
State file
~/Vault/Vantage-OS/permissions.md
Schema:
## Current tier: [1 / 2 / 3]
Last changed: YYYY-MM-DD HH:MM by [the operator]
Reason: [...]
## Tier 2 templates pre-approved (only consulted at Tier 2+)
- [name]: [description, e.g., "rental-fleet standard pre-arrival message"]
## Tier 3 auto-rules (only consulted at Tier 3)
- [rule]: [trigger -> action, e.g., "If rental-fleet trip ends -> send post-trip thank-you using template Z"]
## Audit log (last 30 days)
- YYYY-MM-DD HH:MM | tier | action | resultTier definitions
Tier 1 - Research and draft only (DEFAULT)
- Vantage-OS may research, analyze, draft messages/listings/code/emails.
- Vantage-OS may NOT send, post, commit money, sign anything, or take any action visible to a third party.
- Drafts queue for the operator's explicit per-item approval.
- This is the default for all new sessions and overnight periods.
Tier 2 - Send pre-approved templates
- Everything in Tier 1, plus:
- Vantage-OS may send messages and post listings using templates the operator has pre-approved and added to
permissions.mdunder "Tier 2 templates pre-approved." - Each sent action is logged in the audit log.
- Vantage-OS still may not commit money or sign anything.
- the operator must add templates explicitly. No template = no send.
Tier 3 - Act on documented rules
- Everything in Tier 2, plus:
- Vantage-OS may execute documented rules under "Tier 3 auto-rules" without per-action approval.
- Hard limits regardless of tier:
- No spending >$50 in a single action without the operator's explicit per-action approval
- No trading. the operator trading restrictions apply and the system has no broker access.
- No signing contracts.
- No posting to public social media on the operator's personal accounts.
- No a partner-related actions (her platform, their work) without her explicit OK.
Process
Setting tier
When the operator says "raise to tier 2" or similar:
- Verify the tier change is intentional. Ask: "Tier 2 lets me send pre-approved template messages without per-message approval. Right now you have [list templates] pre-approved. Confirm raise?"
- If raising to Tier 3, list the auto-rules currently configured and confirm.
- Update
permissions.md. Log the change with timestamp and reason. - Notify in chat: "Now Tier N. Blast radius: [list current Tier N capabilities]."
Kill switch
When the operator says "stop", "kill", "shut it down", "emergency":
- Immediately set tier to 1.
- Halt any in-progress sub-agent dispatches.
- Write the kill event to the audit log.
- Ask the operator what triggered the kill so the lesson is captured.
Pre-action check
Before any sub-agent or skill takes an external action, it must consult permissions.md:
- Read current tier.
- Check if action is allowed at this tier.
- If not allowed, refuse and propose what tier would be needed.
- If allowed, perform action and log to audit.
Tier auto-drop overnight
When nightly-wrap runs and the operator will be away for 8+ hours:
- If tier is 2 or 3, default-recommend dropping to 1.
- If the operator explicitly wants to maintain tier overnight, log the override with reason.
Pre-approved Tier 2 template format
### [Template name]
- Channel: [e.g., rental-fleet message, Gmail draft, etc.]
- Trigger: [when this template applies]
- Body:
[exact text, with {{variables}} for substitution]
- Variables: {{var1}} (description), {{var2}} (description)Audit examples
Good entry:
2026-05-17 09:14 | Tier 2 | Sent rental-fleet pre-arrival message to renter Jane D. for Model 3 Performance trip starting 2026-05-17 14:00 | Sent successfullyBad entry (the kind that should trigger the operator's attention):
2026-05-16 02:30 | Tier 3 | Attempted post-trip thank-you to renter Carlos M. | FAILED: rental-fleet MCP unavailable. Queued for retry.Rules
- Default is Tier 1. Always. Sessions start at Tier 1 unless the operator explicitly raises in-session.
- Tier never auto-raises. Only the operator raises.
- Hard limits override tier. Even at Tier 3, the hard limits hold.
- Audit log is append-only. Never edit history.
- If permissions.md is missing or corrupted, default to Tier 1 and warn the operator.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

