imessage

iMessage sending via Mac Mini SSH.

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

Steps

• sendIMessage() - see state/lib/imessage.ts
• readRecent() - see state/lib/imessage.ts

Eval

Actor: the exported functions in state/lib/imessage.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: calls_send_imessage
    kind: deterministic
    check: "The skill execution log must contain a call to the sendIMessage() function. (e.g., check 'state/log/pending-eval.ndjson' for relevant entries indicating function calls)."
  - name: calls_read_recent
    kind: deterministic
    check: "The skill execution log must contain a call to the readRecent() function. (e.g., check 'state/log/pending-eval.ndjson' for relevant entries indicating function calls)."
  - name: output_matches_imessage_api
    kind: judge
    check: "The output of the skill, particularly from readRecent(), should reflect a structure consistent with the iMessage API as defined in 'state/lib/imessage.ts', exhibiting correct message formats and recipient/sender information."
  - name: side_effects_honest
    kind: judge
    check: "Any iMessage sent via sendIMessage() should be verifiable on the target device, and readRecent() should accurately reflect recent messages without unexpected side effects."

imessage - loader

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

Critical Rules

• iMessage send routes through Mac Mini over SSH - there's no first-party iMessage HTTP API. The Mini is the only sending host.
• sendIMessage is irreversible side-effect - keep behind scope-only default per program.md

Commands

| ui dashboard | state/skills/imessage/resources/ui.openui | |invoke: import from state/lib/imessage.ts - sendIMessage(), readRecent() |verify: readRecent() after a send to confirm the message landed in the local store |eval log: state/log/pending-eval.ndjson (manual eval - skill: "imessage")

OpenUI Resource

• Skill-owned OpenUI Lang resource: state/skills/imessage/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

• SSH path to Mac Mini must be reachable - no fallback. If the Mini is offline, sends silently fail; verify with readRecent.
• Mac Mini server context: see mac-mini-server skill / mac-mini-remote-ops skill in the wider catalog if SSH config drifts

Self-Test

An agent reading this should correctly:

1. [ ] Default sendIMessage to scope-only
2. [ ] Verify sends with readRecent, not just trust the SSH return
3. [ ] Recognize the Mac Mini SSH dependency

Self-report

If this loader fell short, append a line:

echo "[$(date -u +%FT%TZ)] imessage: <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)] imessage: <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.