dashboard

snappy-dashboard/api.ts - Base URL for all examples: ``bash BASE="https://backend-dashboard-api.fly.dev" ``

Ported from kernel snappy-dashboard in Phase 0.5. See state/lib/dashboard.ts for the full API surface.

Steps

• See state/lib/dashboard.ts

Eval

Actor: the exported functions in state/lib/dashboard.ts. Auditor: none wired yet - eval is manual (Robert review). File a state/log/pending-eval.ndjson row on each run.

Score convention:

Gotchas

via the Phase 0.5 driver. Only these rewrites were applied: already in state/lib/)

1. realpathSync(process.argv[1]) CLI guard wrapped in try/catch

• See the kernel SKILL.md for the original long-form guidance if you need it

(read-only reference at the kernel path above).

Graduation

This skill is prose. Graduate by defining a deterministic auditor and flipping eval: auto.

Rubric

criteria:
  - name: dashboard_ts_exists
    kind: deterministic
    check: "The file 'state/lib/dashboard.ts' must exist and be accessible."
  - name: dashboard_api_base_url
    kind: deterministic
    check: "The 'dashboard.ts' file or related configuration must use 'https://backend-dashboard-api.fly.dev' as the base URL for API requests."
  - name: log_pending_eval_row
    kind: deterministic
    check: "A new row must be appended to 'state/log/pending-eval.ndjson' for each execution of the skill."

dashboard - loader

Per-turn rules for the dashboard skill. Full reference: state/skills/dashboard/SKILL.md. Do not skip these.

Critical Rules

_(no failures recorded yet - this skill is a Phase 0.5 prose port and the lib is a scaffold stub per state/index.md. No hard-won rules have surfaced yet. Read state/skills/dashboard/SKILL.md and state/lib/dashboard.ts before invoking.)_

Commands

| ui dashboard | state/skills/dashboard/resources/ui.openui | |invoke: HTTP against BASE="https://backend-dashboard-api.fly.dev" via state/lib/dashboard.ts |verify: GET a read-only endpoint before any write |eval log: state/log/pending-eval.ndjson (manual eval - skill: "dashboard")

OpenUI Resource

• Skill-owned OpenUI Lang resource: state/skills/dashboard/resources/ui.openui. Read it before rendering or editing this skill's generated component surface.
• Treat this resource as a first-class artifact of the skill, not a generic chat response. Improve it when the skill's user-facing output needs to become richer.
• System resources compose OpenUI primitives and inherit SnappyChat tokens. Use ui_contract: branded in SKILL.md only for deliberate platform or client visuals.

Known Pitfalls

• Lib is a scaffold stub (state/index.md). Don't assume rich helpers exist - most calls will be raw HTTP.
• Audit-before-push rule applies to dashboards (feedback_audit_before_push.md): don't fan out lints in parallel with irreversible push pods, race lands defects live

Self-Test

An agent reading this should correctly:

1. [ ] Recognize state/lib/dashboard.ts is a stub and may need raw HTTP
2. [ ] Hit backend-dashboard-api.fly.dev not a localhost or kernel path
3. [ ] Serialize audits before pushes, never parallel

Self-report

If this loader fell short, append a line:

echo "[$(date -u +%FT%TZ)] dashboard: <what was missing>" >> state/log/loader-feedback.log

<!-- kernel-ok: historical attribution for the PID-loader pattern. -->

Self-correcting loader (PID feedback)

This is the rule that makes loaders learn. Ported from snappy-kernel, where it demonstrably worked: the snappy-dom-cartographer skill mapped Skool admin UI once, every later ship-agent inherited the full map for free.

Before you finish, do two things:

1. Fix gaps (P - proportional). MANDATORY. If this loader didn't cover your case - if you had to read another file, run an undocumented command, work around a wrong selector, or discover a quirk - you MUST attempt an Edit to this AGENTS.md before you log.

• Default action: edit this file. Surgical. Add the missing line, table

row, or code example where it belongs. No restructuring.

• Only LOGGED is allowed when: the fix needs >10 lines, spans multiple

files, or requires a structural rewrite. In that case the state/regen/drain.sh queue picks it up asynchronously.

• "I didn't have time" / "it's minor" / "the next agent will figure it out"

are NOT valid reasons. Minor gaps compound - that's the whole point of this loop.

• Concrete example of a valid P-fix: discover agent-browser screenshot

takes path positionally not as --output <path>. One line in a table. Edit it in. Do not just log it.

• The goal: the next agent never has to leave the loader.

2. Log the result.

echo "[$(date -u +%FT%TZ)] dashboard: <what was missing or fixed> [FIXED|LOGGED]" >> state/log/loader-feedback.log

• FIXED = you patched this loader inline (P-fix).
• LOGGED = too large for inline; the PostToolUse enqueue + Stop-hook drain

will rewrite the loader from scratch on next session-end.

Do not skip this. Every agent run must leave the system better than it found it. The loader is the setpoint; you are the sensor; the gap is the error signal; closing the gap is the correction.