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 agentmods add skills/levixdd/agentdeskskill/agentdesknpx skills add LeviXDD/AgentDeskSkill --skill agentdeskgit clone --depth 1 https://github.com/LeviXDD/AgentDeskSkillWhat 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 | $0.00096 | $0.08002 |
| Opus 5 | $0.00048 | $0.04001 |
| Sonnet 5 | $0.00019 | $0.01600 |
| Haiku 4.5 | $0.00010 | $0.00800 |
Grade A, and why
agentdesk 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 2d 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 — 402 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AgentDesk
Outcome
Turn a software repository into a controlled multi-session development system:
Versioned task cards, PM-owned canonical state, real independently visible role tasks, role-bound execution, proactive callbacks, immutable Git evidence, explicit acceptance, and recoverable handoff.
The observable loop is non-negotiable:
PM/Leader task
→ verified independent role task named `role_no . role_name`
→ real dispatch delivery
→ dedicated worktree execution and durable report
→ worker proactively messages the PM/Leader source task
→ PM independently accepts and integrates
→ dependencies unlock
→ heartbeat reconciles only if the primary callback path fails
Repository records make this loop recoverable; they do not substitute for creating, addressing, or messaging the real tasks.
When a question needs competing viewpoints before execution, AgentDesk can prepend a bounded consultation loop: one Leader opens one to three read-only consultation tasks, collects independent first-round callbacks, optionally runs one cross-check round, synthesizes disagreements, and asks the Owner to confirm what—if anything—becomes a decision or task card. Consultation is advisory and never substitutes for the execution loop above.
Automate coordination, not authority. Keep product decisions, risky approvals, merging, and release behind their declared gates.
Resolve The Requested Mode
Choose the primary mode from the request and repository state. Consultation may precede PM, but its output does not silently enter execution:
- Initialize — scaffold or upgrade a project workflow.
- Consultation — open zero to three bounded, read-only advisory tasks around one topic, collect their callbacks, synthesize, and request Owner confirmation.
- PM — clarify requirements, configure roles, create and dispatch cards, review deliveries, update state, and unlock dependencies.
- Worker — implement one assigned card inside its scope and produce a delivery report.
- QA / Integration — test a frozen candidate or combine accepted commits under a dedicated card.
- Validate — check project structure and state without changing business code.
- Recover — reconcile conflicting state, lost callbacks, stale revisions, expired leases, or invisible Git evidence.
What ships with it
46 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.
- agents/openai.yaml 430 B
- assets/acceptance-template.md 927 B
- assets/consultation-brief-template.md 2.4 KB
- assets/consultation-record-template.yaml 1.5 KB
- assets/consultation-response-r2-template.md 1.1 KB
- assets/consultation-response-template.md 1.0 KB
- assets/consultation-synthesis-template.md 2.0 KB
- assets/delivery-report-template.md 1.9 KB
- assets/project-template/.agentdesk/runtime/consultations.yaml 105 B
- assets/project-template/.agentdesk/runtime/model-bindings.yaml 94 B
- assets/project-template/.agentdesk/runtime/routes.yaml 389 B
- assets/project-template/.agentdesk/runtime/transport-receipts.yaml 112 B
- assets/project-template/AGENTS.md 4.0 KB
- assets/project-template/docs/pm/acceptances/.gitkeep 39 B
- assets/project-template/docs/pm/AGENTDESK.lock.json 3.4 KB
- assets/project-template/docs/pm/BOARD.md 3.3 KB
- assets/project-template/docs/pm/CHECKS.yaml 237 B
- assets/project-template/docs/pm/CONSULTATION-POLICY.yaml 348 B
- assets/project-template/docs/pm/CONSULTATIONS.md 955 B
- assets/project-template/docs/pm/DECISIONS.md 654 B
- assets/project-template/docs/pm/events/.gitkeep 39 B
- assets/project-template/docs/pm/outbox/.gitkeep 39 B
- assets/project-template/docs/pm/PM-PLAYBOOK.md 15 KB
- assets/project-template/docs/pm/reports/.gitkeep 39 B
- assets/project-template/docs/pm/ROLE-POLICIES.yaml 1.0 KB
- assets/project-template/docs/pm/ROLES.md 2.8 KB
- assets/project-template/docs/pm/state/tasks.yaml 265 B
- assets/project-template/docs/pm/STATUS.md 1.3 KB
- assets/project-template/docs/pm/tasks/.gitkeep 39 B
- assets/task-card-template.md 2.0 KB
- references/codex-runtime-adapter.md 19 KB
- references/consultation-protocol.md 32 KB
- references/events-outbox-and-validation.md 28 KB
- references/protocol.md 34 KB
- references/runbooks-and-recovery.md 40 KB
- references/schemas-and-templates.md 28 KB
- references/versioning-and-upgrades.md 19 KB
- release-manifest.json 3.5 KB
- scripts/adopt_legacy_project.py 98 KB runs code
- scripts/check_compatibility.py 65 KB runs code
- scripts/init_project.py 62 KB runs code
- scripts/render_views.py 33 KB runs code
- scripts/select_model.py 31 KB runs code
- scripts/validate_consultations.py 131 KB runs code
- scripts/validate_project.py 166 KB runs code
- scripts/validate_runtime.py 21 KB runs code
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.
- 2d ago First seen · 402 lines · 96 tokens per session scan A 3349ba90d25c
agentdesk is a skill published in the GitHub repository LeviXDD/AgentDeskSkill (10 stars, last pushed 1mo ago), licensed MIT. It adds 96 tokens to every session and 8,002 once invoked, about $0.0005 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
mission-control
Orchestrate multi-loop background operations via the Mission Control dashboard — start sessions, dispatch missions, monitor, and stop.
fabric-swarm
Creates a self-organizing team of persistent Pi Fabric actors with durable topics, mailboxes, and compare-and-swap tasks. Use for messenger-like collaboration and long-lived delegated work.
multi_agents
Enables multi-agent collaboration through teams, task delegation, and coordinated workflows.
orch
AI agent orchestrator — manage teams of AI agents that work on your codebase in parallel. Use when the user wants to: run multiple agents, coordinate AI work, deploy agent teams, manage tasks/goals/agents, check orchestrator status, or mentions 'orch', 'orchestry', 'agents team', 'agent orchestration'.
t0-orchestrator
Master orchestration for the VNX multi-terminal system. Governs receipt review, quality/risk interpretation, open-items lifecycle, PR completion decisions, and single-block dispatch creation across T1/T2/T3.
control-centre
Multi-project Control Centre supervisor. Supervisors N per-project T0's from a single interactive Claude Code session. Read-only orchestration — no code writes.