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/opensesh/canvas-to-code/dashboardgit clone --depth 1 https://github.com/opensesh/canvas-to-codeWrote 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/opensesh/canvas-to-code/dashboard)<a href="https://agentmods.dev/commands/opensesh/canvas-to-code/dashboard"><img src="https://agentmods.dev/badge/commands/opensesh/canvas-to-code/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 | $0.00018 | $0.01340 |
| Opus 5 | $0.00009 | $0.00670 |
| Sonnet 5 | $0.00004 | $0.00268 |
| Haiku 4.5 | $0.00002 | $0.00134 |
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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/canvas-to-code:dashboard — Work timeline
Single-pane view of every feature ever bridged. Reads .canvas-to-code/state/*/status.json plus git log and gh pr view for PR status. No agents — pure aggregation.
What it shows
Cross-feature (no args) — every feature in .canvas-to-code/state/, one row each:
- Feature slug + phase + current gate
- Started · last touched · completed (— if still in flight)
- Slices: merged / total, with the in-flight slice flagged
- Slice PRs (#numbers + status: open / merged / closed)
- Swap PR (if reached) + status
- Spike doc link · plan doc link
- Component reuse rollup:
+N / −M(new introduced / reused from DS)
Single feature (--feature <name>) — adds:
- Full gateLog with ISO timestamps (every Gate 0–10 entry, pass / warn / fail)
- Source shape:
iter(withsubpage+ iter path) orflat - Per-slice detail: title, branch, files, started_at, merged_at, PR number, LOC
- Component map aggregate by tier (base / ds / custom-shared / custom-page / net-new)
- Guardrail violation totals
- Icon gaps
Sample (cross-feature)
Canvas-to-Code — work timeline
==============================
Features: 3 (1 done · 2 in flight)
Last activity: 2026-05-19 17:42
| Feature | Phase | Gate | Started | Last | Slices | Swap PR | New / Reused |
|------------------|-------|------|------------|------------|--------|---------|--------------|
| brand-hub-hifi | done | 10/10| 2026-05-12 | 2026-05-12 | 6 / 6 | #319 ✓ | +24 / −23 |
| spaces-redesign | slice | 7/10 | 2026-06-04 | 2026-06-12 | 3 / 6 | — | +9 / −18 |
| account-shell | plan | 7/10 | 2026-06-10 | 2026-06-15 | 0 / 4 | — | +5 / −10 |
Sample (--feature spaces-redesign)
spaces-redesign — Phase: slice (3 / 6)
======================================
Target: /spaces (existing)
Source: claude-design (shape: flat)
Started: 2026-06-04T09:14:08Z
Last touched: 2026-06-12T16:30:51Z
Spike: docs/spikes/design-system/2026-06/2026-06-04-spaces-redesign-bridge.md
Plan: .canvas-to-code/state/spaces-redesign/plan.md
Gates:
✓ 0 Intake 2026-06-04T09:14:08Z
✓ 1 Materials 2026-06-04T09:17:22Z
⚠ 2 DS alignment 2026-06-04T09:19:30Z (warn: synthetic source)
✓ 3 Target audit 2026-06-04T09:42:11Z
✓ 4 Scope 2026-06-04T10:05:44Z
✓ 5 Component mapping 2026-06-04T11:18:02Z (47 units)
✓ 6 Data binding 2026-06-04T11:51:09Z
✓ 7 Slice plan 2026-06-04T12:14:33Z
⏳ 8 Pre-slice (slice 3) in progress
◌ 9 Pre-swap pending
◌ 10 Pre-retro pending
Slices:
1 ✓ scaffold + .claude-design convention #341 150 LOC merged 2026-06-05
2 ✓ 3-tab nav + collapsible overview #342 250 LOC merged 2026-06-08
3 ⏳ PillarCard + 8-card grid (mock) #343 draft started 2026-06-12
4 ◌ wire Logo / Colors / Typography
5 ◌ visual Version History page
6 ◌ swap to /spaces, delete dropped routes
Component map: 47 units
base: 19 reused / 0 new
ds: 4 reused / 1 new
custom-shared: 0 reused / 8 new
custom-page: 12 new
net-new: 3 new
Guardrails: devProps 4 · border-2 1 · ring-2 2 · raw-hex 0 · array-index-keys 8
Icon gaps: slack, asterisk-4-point
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 · 110 lines · 18 tokens per session scan A b0062f650ed3
dashboard is a command published in the GitHub repository opensesh/canvas-to-code (6 stars, last pushed 2mo ago), licensed MIT. It adds 18 tokens to every session and 1,340 once invoked, about $0.0001 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 commands, from other repositories
onboard
You are an expert onboarding specialist and knowledge transfer architect with deep experience in remote-first organizations, technical team integration, and accelerated learning methodologies. Your role is to ensure smooth, comprehensive onboarding that transforms new team members into productive contributors while…
feature-development
Orchestrate end-to-end feature development from requirements to production deployment.
legacy-modernize
Orchestrate a comprehensive legacy system modernization using the strangler fig pattern, enabling gradual replacement of outdated components while maintaining continuous business operations through expert agent coordination.
workflow-design
Exécuter la phase de Conception (Solutioning) - spécification technique et architecture.
sprint
Équipe de Développement Sprint - Implémentation parallèle de stories utilisant les Agent Teams.
speckit.companion.living-move
Move a living spec between central and colocated storage — file, tiers, and registry together (opt-in, reversible).