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 commands/paulonasc/orchestra/dashboardgit clone --depth 1 https://github.com/paulonasc/orchestraWrote 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/paulonasc/orchestra/dashboard)<a href="https://agentmods.dev/commands/paulonasc/orchestra/dashboard"><img src="https://agentmods.dev/badge/commands/paulonasc/orchestra/dashboard.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.01861 |
| Opus 5 | $0.00000 | $0.00931 |
| Sonnet 5 | $0.00000 | $0.00372 |
| Haiku 4.5 | $0.00000 | $0.00186 |
Grade A, and why
dashboard 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 4d 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 — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/o — Executive dashboard
Read all Orchestra state files and render a top-down dashboard. Start high-level, then drill down. The user should understand the project in 5 seconds from the top section alone.
Before rendering: If heartbeat is not yet scheduled this session (check state/sessions/{session-id}.md for heartbeat_scheduled: true — but remember this flag may be stale from a prior session), run /o heartbeat silently first. This is the ONLY place that triggers heartbeat setup — hooks do NOT trigger it.
Concurrent sessions check: Before rendering, check state/sessions/ for multiple active session files. If multiple files exist, add an "Active sessions" section after Section 0:
## Active sessions (2)
20260324-143022-12345 Working on: 001-honestclaw-mvp — API scaffold
20260324-144510-67890 Working on: 003-compress-pipeline — ffmpeg config
Show each session's ID and the first line of "Working on" from its file. If only one session file (or none), skip this section entirely.
Section 0 — Thread health (one line)
Count threads by status. Show at the top so the user instantly sees scope:
🔥 2 active 📦 8 completed 🗑️ 1 abandoned
Only show categories that have items. If all threads are active, just show 🔥 3 active.
Section 1 — Roadmap (where are we?)
Read threads/*/progress.yaml files and aggregate — but only active threads. Completed and abandoned threads are done; don't include them in the roadmap percentage. Show every milestone across active threads. The user needs to see the full journey of what's in flight: where they are, what's ahead, and overall completion of active work.
## Roadmap (overall: 49% — 26/53 items done)
M0 Scaffolding & CI/CD ████████░░ 87% (26/30) ← you are here
M1 Identity & Auth ░░░░░░░░░░ 0% (0/8)
M2 Core Features ░░░░░░░░░░ 0% (0/10)
M3 Integrations ░░░░░░░░░░ 0% (0/3)
M4 Launch & Hardening ░░░░░░░░░░ 0% (0/2)
The overall percentage is critical. Sum all items across all milestones: done / total. Show it in the header so the user instantly knows "we're 49% through the whole project."
If a thread's progress.yaml only has the current milestone defined, flag this to the user: "Only M0 is defined for this thread. Want me to add the remaining milestones from the plan so you can see the full roadmap?"
If milestones don't have descriptions, derive them from the thread's plan.md or spec.md.
Section 2 — Needs your attention
Surface only things that require the human's input or approval:
## Needs your attention
⚠ 2 verification items PENDING — need AWS credentials (infra terraform validate/plan)
⚠ Decision needed — CI/CD provider (GitHub Actions vs CircleCI) not yet decided
📬 3 new handoffs since last session
Categories: blocked items needing human action, pending verification needing manual testing or credentials, undecided decisions, unread handoffs.
Section 3 — Recently completed
What shipped since the user last checked. Pull from today's daily log and recent handoffs:
## Recently completed
- API scaffold: NestJS + Kysely + health endpoint (api)
- Frontend scaffold: Next.js + Tailwind + shadcn (frontend)
- Infra: Terraform modules for ECS, RDS, ElastiCache (infra)
Section 4 — Risks
Read ## Risks from active thread specs. Surface any identified risks:
## Risks
- Terraform state drift if multiple agents run apply concurrently (infra)
- No staging environment yet — can't integration test across repos
If no risks section exists in any active thread, skip this section silently.
Section 5 — Recent decisions
Show the last 3-5 decisions from decisions/ with their reasoning:
## Recent decisions
001 us-west-2 — Chose us-west-2 for all AWS services. Reason: lowest latency to west coast users, broadest service availability.
Footer — self-documenting navigation + contextual hint
The nav bar must be self-documenting — every command has a brief description so the user never has to look up docs. Then show ONE contextual hint.
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.
- 4d ago First seen · 154 lines · 0 tokens per session scan A f6233697d2c7
dashboard is a command published in the GitHub repository paulonasc/orchestra (15 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,861 tokens. 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
project-recap
Generate a visual project recap for context switching.
os-meeting
快速创建和管理AI团队会议.
workspace
Testany Workspace, 管理工作空间,成员权限,团队组织.
standup
Show a daily standup summary with completed, in-progress, and blocked tasks across all active epics.
m-task-planner
Target: $ARGUMENTS (Default: requirement document(s) discovered in the project).
triage-issues
Launch the Issue Triage Agent (Haiku) to categorize and prioritize GitHub issues.