admin
/admin
Act for an org admin — the admin API (scope directory, per-scope config & SOUL, any scope's memory, transcripts & captured prompts, files, user roster, audit/errors/metrics/egress) accepts your token when the user you're talking to is an org admin and started this turn themselves. Use when an admin asks you to inspect or change anything org-wide or in another scope, or anyone asks whether they're an admin.
- Author
- evolvingagentslabs ↗
- Repository
- evolving-agents ↗
- Licence
- Apache-2.0
- Last repository change
- 24.10.2026
Assessment and security
- Files in this package
- 1
- Scripts
- 0
- HTML comments
- 0
- URLs in SKILL.md
- 0
No signals detected. Repository changed on 24.10.2026, without references to retired models or APIs.
Apache-2.0, otwarta: można używać i zmieniać, z zachowaniem licencji i informacji o zmianach.
What it does and when to use it
Act for an org admin — the admin API (scope directory, per-scope config & SOUL, any scope's memory, transcripts & captured prompts, files, user roster, audit/errors/metrics/egress) accepts your token when the user you're talking to is an org admin and started this turn themselves. Use when an admin asks you to inspect or change anything org-wide or in another scope, or anyone asks whether they're an admin.
Original author description
Act for an org admin — the admin API (scope directory, per-scope config & SOUL, any scope's memory, transcripts & captured prompts, files, user roster, audit/errors/metrics/egress) accepts your token when the user you're talking to is an org admin and started this turn themselves. Use when an admin asks you to inspect or change anything org-wide or in another scope, or anyone asks whether they're an admin.
How it works
- Finding the scope
- Read & govern a scope's config
- Read & fix any scope's memory
- Inspect activity & content
- Observability
- Admin grants (promote / revoke)
- Failure modes
SKILL.md preview
---
name: admin
description: Act for an org admin — the admin API (scope directory, per-scope config & SOUL, any scope's memory, transcripts & captured prompts, files, user roster, audit/errors/metrics/egress) accepts your token when the user you're talking to is an org admin and started this turn themselves. Use when an admin asks you to inspect or change anything org-wide or in another scope, or anyone asks whether they're an admin.
---
# admin — act for an org admin, from chat
A connector skill: no new tool. When the chatting user is an org admin (your system
prompt says so — "Acting for an org admin"), the `/v1/admin/*` endpoints accept your
token. You are acting **as them**: authorization is re-checked against the live grant
store on every call, and every call is audited under their name. Two standing rules:
**confirm before any mutation** (state exactly what you'll change and where), and report
afterwards exactly what changed. Reads are fine to just do.
Three limits the API enforces (don't offer what it will refuse):
- Your token elevates only on turns the admin **started themselves** — on autonomous
runs (crons, webhooks) the admin plane refuses it, whoever owns the run.
- Reads that return private content — transcripts, files, notebooks, logs, another
scope's config — only work from a **DM** with the admin. Two exceptions: org-targeted
memory/config reads work anywhere (org content is ambient to every conversation), and
session reads work from a scope whose `admin-session-reads` flag an org admin turned
on — a per-room delegation: any turn in that room (including autonomous wakes) may
read any scope's transcripts and captured prompts, acting and audited as the admin
who set the flag (re-checked live — revoking their admin grant closes it). Because
it keys the boundary, that one flag is itself settable only from a DM (or the
portal). Other mutations work anywhere; the room sees
what changed, by design.
- **Grant changes (promote/revoke) are portal-only** through you — see below.
All calls share one shape — only method/path/body vary:
```bash
curl -fsS -H "x-agent-capability: $AGENT_API_TOKEN" "$AGENT_API_URL/v1/admin/..."
```
Anyone can check admin status (this is also how you answer "am I an admin?"):
```bash
GET /v1/admin/whoami → {"isAdmin":true,"role":"org_admin","scopeId":"org:…"} or {"isAdmin":false}
```
## Finding the scope
Most endpoints take `?scope=<scopeId>` (`org:<org>`, `personal:<user>`, `channel:<id>`).
Don't guess ids — list them:
```bash
GET /v1/admin/scopes → every scope with display labels (#channel names, people) and what lives there
```
## Read & govern a scope's config
```bash
GET /v1/admin/scopes/<scopeId> → resolved config: commandPolicy, soul (+version), egress, flags, connectors, serviceCredentials
PUT /v1/admin/scopes/<scopeId>/<resource> → resource ∈ soul | command-policy | egress |
admin-session-reads | connectors | service-credentials |
base-model (org-wide LLM; body { modelId } — e.g. gpt-5.5; empty string clears)
```
GET first, then PUT the corrected value (`soul` takes `{content}`, `egress` takes
`{allowedHosts,deniedHosts}`, the toggles take `{on}`). Changes apply next turn.
## Read & fix any scope's memory
```bash
GET /v1/admin/memory?scope=<scopeId> → that scope's whole notebook
PUT /v1/admin/memory?scope=<scopeId> {"content":"…full replacement…"}
```
(For "remember this org-wide" you don't need the admin plane at all — `"scope":"org"`
on the memory self-API is the lighter path; see the memory skill.)
## Inspect activity & content
```bash
GET /v1/admin/sessions?scope=&limit=&offset= → conversation listing (turns, last activity)
GET /v1/admin/sessions/<id>?scope= → a transcript
GET /v1/admin/sessions/<id>/llm?scope= → captured provider requests — what the model actually saw (debugging "why did it do X")
GET /v1/admin/runs?scope= → queued/in-flight/recent runs
GET /v1/admin/files?scope= → document store; read?id= / download?id= for content
GET /v1/admin/volumes?scope= → a scope's computer/backup contents (sizes only)
GET /v1/admin/crons|deployments|skills?scope= → artifacts by owner
```
## Observability
```bash
GET /v1/admin/audit?scope= GET /v1/admin/errors?scope= GET /v1/admin/metrics?scope=
GET /v1/admin/egress?scope= GET /v1/admin/retention
GET /v1/admin/users → roster + admin status (org-wide)
```
## Admin grants (promote / revoke)
Not available through you: who governs the org changes only in the admin dashboard,
where the admin acts directly. If asked, point them there — don't try the API
(`POST/DELETE /v1/admin/grants` refuses agent tokens).
## Failure modes
- `403 admin grant required for this scope` — the user isn't an org admin (or was just
revoked). Say so; don't retry or work around it.
- `403 … require a turn the admin started themselves` — this is an autonomous run
(cron/webhook); admin actions only ride turns the admin personally initiated. Say so.
- `403 … returns private content — ask the agent in a DM` — you're in a shared room;
tell the admin to ask again in a DM with you (or, for session reads they want
recurring in this room, to turn on this scope's `admin-session-reads` flag — from
their DM, never from here).
- `403 … grant changes (promote/revoke) are portal-only` — point them at the dashboard.
- `403 capability token not valid for this route` — this core predates agent admin
access; the user must use the admin dashboard.
Versions
| Repository | Score | Licence |
|---|---|---|
| This page · evolvingagentslabs/evolving-agents | 100 | Apache-2.0 |
| yc-software/qm | 100 | MIT |
| grafana/skills | 100 | Apache-2.0 |
| devv-shayan/8x-hackathon | 100 | MIT |
| markusleben/ha-nova | 90 | MIT |
Database snapshot: 13.11.2026 · package version 2de80b256f71 (SHA-256 digest of the entire package)
Downloads in the last 30 days: 0 · ranking
Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.
Similar skills
- 90company-setup
Build the company memory every teammate reads, with an admin. Use only when an admin asks to set up (or refresh) company memory. - 95agent-admin
Query and manage Shipwright agents via the admin API — cron jobs, env vars, tool permissions, API tokens, and plugins. Use to configure the running agent, manage its schedules, inspect another agent's config, or provision a new agent. - 100iblai-vibe-memory-guide
What memory means for an ibl.ai app and which surface to mount for which audience — user global memories, per-agent memories by category, shared agent knowledge (the Memory tab's Shared Memory sub-tab), the org/agent/user gates that decide whether memory is on, and the SDK hooks… - 100iblai-api-org
Read and write an ibl.ai organization's org-wide settings via the platform API — the org metadata object holding Default Agent, Help Center URL, Chat Area Width, and feature toggles (Help/Accessibility menus, Community Agents, Report Inappropriate Content). Use when configuring org-wide behavior.