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.
npx skills add rundesk-ai/rundesk-cli --skill managing-rundeskgit clone --depth 1 https://github.com/rundesk-ai/rundesk-cliWrote 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/skills/rundesk-ai/rundesk-cli/managing-rundesk)<a href="https://agentmods.dev/skills/rundesk-ai/rundesk-cli/managing-rundesk"><img src="https://agentmods.dev/badge/skills/rundesk-ai/rundesk-cli/managing-rundesk/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/skills/rundesk-ai/rundesk-cli/managing-rundesk"><img src="https://agentmods.dev/badge/skills/rundesk-ai/rundesk-cli/managing-rundesk.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 | $0.00079 | $0.01176 |
| Opus 5 | $0.00039 | $0.00588 |
| Sonnet 5 | $0.00016 | $0.00235 |
| Haiku 4.5 | $0.00008 | $0.00118 |
Grade A, and why
managing-rundesk scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Manage Rundesk
Use Rundesk's commands to answer questions about this install. Do not guess at its state or paths.
Use the right install
Run "$RUNDESK_COMMAND", never bare rundesk. It is the absolute command for the install running
this turn. $RUNDESK_HOME already points to that install; do not change it or introduce another
location.
"$RUNDESK_COMMAND" status
"$RUNDESK_COMMAND" --help
Treat generated help as authoritative. If a verb is absent, Rundesk cannot perform it. A command
exits 0 when it answered or completed, 1 when understood but not completed, and 2 for invalid
command syntax. Never report success from wording alone; read the exit code and result.
Common entry points
| Priority | Need | Command |
|---|---|---|
| 1 | Prove which install this is and whether it is healthy | "$RUNDESK_COMMAND" status |
| 2 | See the agents and their providers | "$RUNDESK_COMMAND" agents |
| 3 | See whether gateways are running | "$RUNDESK_COMMAND" gateways |
| 4 | Explain gateway trouble | "$RUNDESK_COMMAND" gateways logs <agent> |
| 5 | Check provider, channel, and skill readiness | "$RUNDESK_COMMAND" providers check <provider> · "$RUNDESK_COMMAND" channels doctor <agent> · "$RUNDESK_COMMAND" skills doctor <agent> |
| 6 | Protect approved risky work | "$RUNDESK_COMMAND" backups save |
Choose the narrowest command that answers the request. Before a mutation, inspect only enough state to identify the exact target and consequence. Most groups list when called with no subcommand.
Safety boundaries
- Never open or edit Rundesk databases, conversation records, or lock files directly. If a command fails, use documented read-only surfaces or report it; do not bypass the command with file tools.
- Never stop your own gateway. Restarting it is allowed: Rundesk queues the restart until the active turn finishes, then brings the gateway back online.
- Require an explicit request for agent removal, schedule removal, backup restore, uninstall, purge, or forced gateway shutdown. Name the exact target.
- Run a guarded command without
--confirmfirst when it offers a preview. Add--confirmonly after the preview matches the request. - Save a backup before an approved destructive change. A backup contains the sealed credential store and its key, so protect its location as credential-bearing data.
- Never ask for a credential in chat or pass one as an argument. Tell the owner to run
"$RUNDESK_COMMAND" env set <NAME>in their own terminal. - Prefer diagnosis before restart: inspect status, listings, logs, and the relevant
doctororcheckcommand.
What ships with it
17 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/agent-instructions.md 12 KB
- references/agents.md 5.9 KB
- references/backups.md 2.1 KB
- references/channels.md 6.6 KB
- references/configuration.md 3.6 KB
- references/conversations.md 5.3 KB
- references/gateways.md 3.1 KB
- references/lifecycle.md 3.7 KB
- references/maintenance.md 4.9 KB
- references/oauth-login.md 3.4 KB
- references/permissions.md 2.8 KB
- references/providers.md 2.8 KB
- references/retrospective.md 3.8 KB
- references/schedules.md 6.4 KB
- references/self-improvement.md 11 KB
- references/skills.md 6.4 KB
- references/teams.md 3.0 KB
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.
- 5d ago Changed b9efabf60be5
- 10d ago First seen · 80 lines · 79 tokens per session scan A e69daa29e5a1
managing-rundesk is a skill published in the GitHub repository rundesk-ai/rundesk-cli (6 stars, last pushed 6d ago), licensed MIT. It adds 79 tokens to every session and 1,176 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
hive.chart-creation-foundations
Required reading whenever any chart tool is available. Teaches the one-tool embedding contract (call chartrender → live chart appears in chat AND a downloadable PNG lands in the queen session dir), the ECharts (data viz) vs Mermaid (structural diagrams) decision, the BI/financial-grade aesthetic baseline (no…
browser-edge-cases
SOP for debugging browser automation failures on complex websites. Use when browser tools fail on specific sites like LinkedIn, Twitter/X, SPAs, or sites with Shadow DOM.
fork-fleet
Fork divergence monitor - tracks where the fleet's active forks diverge in CODE (unique commits, new/modified skills) and CONFIG (enable/var/model/schedule vs upstream), gated on real change.
github-trending
Curated trending across GitHub repos and the Hugging Face Hub (models, datasets, spaces) - filtered, clustered, and labeled by momentum with a one-line why-notable per pick.
pack-submit
Package one of this agent's own skills as a standalone community pack and submit it to the aeon registry as a PR.
shiplog
Recap of everything shipped since the last run - cross-repo PRs, security fixes, star deltas, and X traction, synthesized into a digest article and a ready-to-post shiplog in your voice.