clients

Client lifecycle router for all snappy-* skills.

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

Steps

• getClients() - see state/lib/clients.ts
• getClientHealth() - see state/lib/clients.ts
• sendSlackMessage() - see state/lib/clients.ts
• sendText() - see state/lib/clients.ts
• listContacts() - see state/lib/clients.ts

Eval

Actor: the exported functions in state/lib/clients.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_correct_function
    kind: deterministic
    check: "The skill calls the `state/lib/clients.ts` function corresponding to the provided input, e.g., `getClients()` for `getClients_input`."
  - name: handles_all_inputs
    kind: deterministic
    check: "The skill has logic to correctly route and process all declared inputs: `getClients_input`, `getClientHealth_input`, `sendSlackMessage_input`, `sendText_input`, and `listContacts_input`."
  - name: uses_correct_api_surface
    kind: deterministic
    check: "The skill exclusively uses the API surface defined in `state/lib/clients.ts` for client lifecycle operations without introducing external dependencies for these functionalities."
  - name: logs_pending_eval_row
    kind: deterministic
    check: "Upon execution, a row is appended to `state/log/pending-eval.ndjson` as per the manual evaluation instructions."

clients - loader

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

Critical Rules

_(no failures recorded yet - Phase 0.5 mechanical port from kernel snappy-clients. Read state/skills/clients/SKILL.md and state/lib/clients.ts before invoking.)_

• sendSlackMessage and sendText are write-effect - surface through scope/apply gate, never auto-fire
• ALWAYS use getClients() as the source of truth for the active-client list - don't read sources/clients/* ad-hoc

Commands

| ui dashboard | state/skills/clients/resources/ui.openui | |invoke: import { getClients, getClientHealth, sendSlackMessage, sendText, listContacts } from "state/lib/clients.ts" |verify: npx tsx -e 'import("/Users/robertboulos/projects/snappy-os/state/lib/clients.ts").then(m => console.log(Object.keys(m)))' |eval log: state/log/pending-eval.ndjson (skill: "clients")

OpenUI Resource

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

• Phase 0.5 port - only mechanical rewrites applied (settings/load → env, sibling rewires, CLI guard)
• The per-client libs (client-ray, client-scott, client-orbiter, client-total) wrap channel-specific logic - prefer those when the client is known

Self-Test

An agent reading this should correctly:

1. [ ] Treat sendSlackMessage / sendText as write-effect (gate before applying)
2. [ ] Use getClients() rather than reading the sources index directly
3. [ ] Defer to per-client libs when the client is known

Self-report

If this loader fell short, append a line:

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