Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/desplega-ai/agent-swarmWrote 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/desplega-ai/agent-swarm/user-management)<a href="https://agentmods.dev/commands/desplega-ai/agent-swarm/user-management"><img src="https://agentmods.dev/badge/commands/desplega-ai/agent-swarm/user-management/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/desplega-ai/agent-swarm/user-management"><img src="https://agentmods.dev/badge/commands/desplega-ai/agent-swarm/user-management.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 | $0.00046 | $0.01766 |
| Opus 5 | $0.00023 | $0.00883 |
| Sonnet 5 | $0.00009 | $0.00353 |
| Haiku 4.5 | $0.00005 | $0.00177 |
Grade A, and why
user-management 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 9d 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 — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
User Management
Manage the swarm's user registry — creating, updating, resolving, and listing users. Users link human identities across platforms (Slack, GitHub, GitLab, Linear, email) so the swarm can track who requested work.
Migration note (2026-05): the old top-level identity fields (
slackUserId,linearUserId,githubUsername,gitlabUsername) and the fuzzynamelookup were removed in lockstep with the user-identity refactor. Use the new{kind, externalId}shape instead. Old payloads now fail Zod validation at runtime — there is no compatibility shim.
When to Create Users
Create a new user when:
- An unknown Slack user sends a message to the swarm (
resolve-userwith{kind: "slack", externalId: "<U_X>"}returns no match) - An unknown GitHub user opens an issue or PR that triggers a task
- An unknown GitLab user creates an issue or MR
- An unknown Linear user is assigned to or creates a synced issue
- A human explicitly asks to be registered
Do NOT create duplicate users. Always call resolve-user first — by {kind, externalId} AND, when you have it, by email — to check if the person already exists under a different platform identity.
Tools
Two MCP tools handle user management:
resolve-user — Find an existing user
Looks up a user by an (kind, externalId) pair OR by email (primary or alias). Use this BEFORE creating a new user. Caller MUST supply either (kind + externalId) OR email — empty input is rejected.
# Lookup by platform identity
resolve-user with:
kind: "slack"
externalId: "U12345"
# OR
resolve-user with:
kind: "github"
externalId: "octocat"
# OR
resolve-user with:
kind: "gitlab"
externalId: "octocat"
# OR
resolve-user with:
kind: "linear"
externalId: "uuid-from-linear"
# OR lookup by email (primary or alias)
resolve-user with:
email: "[email protected]"
Email lookup is case-insensitive and checks the primary email column AND every entry in emailAliases.
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.
- 9d ago First seen · 159 lines · 46 tokens per session scan A 278be4e40661
user-management is a command published in the GitHub repository desplega-ai/agent-swarm (754 stars, last pushed today), licensed MIT. It adds 46 tokens to every session and 1,766 once invoked, about $0.0002 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
distill
Distill repository files into the RLM Summary Ledger using agentic intelligence (fast) or Swarm Workers (offline batch).
distill-agent
High-speed RLM distillation of project documentation using agentic intelligence.
os-loop
Run a full OS improvement cycle — execute, eval, emit friction events, close with post-run metrics, and trigger a Triple-Loop Retrospective if the friction threshold is crossed.
os-init
Bootstrap the project by triggering the agentic-os-setup conversational architect.
os-memory
Force garbage collection and conflict resolution on the tiered memory system.
os-architect
Front-door intake for Agentic OS evolution — classifies intent, audits existing capabilities, proposes a path (A/B/C), and dispatches implementation work via Copilot CLI.