pending-approvals
Skill4 starsChanged 5 months agoMITView on GitHub
Use when the user asks to list, inspect, approve, reject, or revoke pending approvals -- "qué aprobaciones tengo pendientes", "aprueba esto", "rechaza esa aprobación", "revoca el permiso", "show pending approvals", "approve this".
In this repository42 other files it gives its agents.
- agent-contract-handoffSkill
- agent-creationSkill
- agent-protocolSkill
- agent-responseSkill
- blog-writingSkill
- brief-specSkill
- cli-loginSkill
- code-reviewSkill
- code-standardsSkill
- command-executionSkill
- deck-builderSkill
- dispatchSkill
- executionSkill
- fast-queriesSkill
- gaia-auditSkill
- gaia-checkSkill
- gaia-patternsSkill
- gaia-plannerSkill
- gaia-releaseSkill
- gaia-researchSkill
- gaia-verifySkill
- ghostwritingSkill
- git-conventionsSkill
- gmail-policySkill
- gmail-triageSkill
- gws-setupSkill
- human-registerSkill
- investigationSkill
- memorySkill
- orchestrator-present-approvalSkill
- remindersSkill
- security-tiersSkill
- session-channelsSkill
- session-reflectionSkill
- skill-creationSkill
- subagent-request-approvalSkill
- technical-explanationSkill
- technical-writingSkill
- ticket-writingSkill
- verification-oracleSkill
- verification-rubricSkill
- visual-verifySkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 26
Every reader names an approval by one derived state.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Pending Approvals
Pending approvals are not resurfaced in later sessions on their own. Recovery
is explicit: the user asks to list pendings or supplies an approval id. Every
lookup and single-item decision takes the complete canonical
P-<32 lowercase hex> id; a short label is never a lookup key.
Reading
gaia approvals pending-- the undecided requests, all sessions by default (--session <id>narrows).gaia approvals list-- grants with STATUS, GRANT_STATE and OUTCOME columns, and the undecided requests beneath them with their STATE (--session,--orphans-onlyfor the orphaned ones,--json).gaia approvals show <approval_id>-- one approval: State, Outcome, Reason, Requester, Window, Directory, the grant and the sealed payload.gaia approvals history [<approval_id>]-- recent approvals, or one approval's event chain.gaia approvals stats-- counts by state and outcome.
Every reader names an approval by one derived state; reference.md lists them.
Deciding
The user decides on the signature Gaia shows (orchestrator-present-approval).
From a terminal, the user can also run gaia approvals approve <approval_id>:
it creates the grant exactly as Approve on the question does.
The orchestrator withdraws but never approves. It may run
gaia approvals reject <approval_id> (a pending request becomes rejected) and
gaia approvals revoke <approval_id> (an armed grant can no longer be used) --
for example to retire an orphaned request. Both accept --reason <text>, which
the withdrawal event records. Approving, replaying, and the bulk
verbs (reject --all, reject-all, clean) are the user's, or a specialist's
when the user asks for them.
A set that ended failed is frozen: show its completed, failed and untouched
commands as history; anything still needed is a new request.
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.

