snappy-agents

One job: flip the byline from the default 1-line summary to a full per-agent detail view. Each row shows the agent's state (running / ok / late / broken / paused) + last-run age + a verb to fix the broken/late ones. Auto-reverts to default after 5 min.

Usage

/snappy-agents

No arguments. Single side effect: writes state/log/byline-view.json.

Steps

1. Run:

   python3 -c "import json,datetime; open('$HOME/projects/snappy-os/state/log/byline-view.json','w').write(json.dumps({'view':'agents','set_at':datetime.datetime.now(datetime.UTC).strftime('%Y-%m-%dT%H:%M:%SZ')})+'\n')"

1. Confirm by running bash $HOME/projects/snappy-os/state/bin/statusline.sh

and showing the operator the rendered output verbatim.

1. Tell the operator:

• the view is set
• it auto-reverts in 5 min
• to revert sooner: /snappy-default

1. Log eval row to state/log/evals.ndjson:

{ts, skill:"snappy-agents", verb:"set-view", score: 1 if file written else 0}

Why

The default byline is two lines - fits the prompt strip but hides 90% of agent state. The TUI is too far to reach mid-conversation. Slash-command- flipped views are the middle ground: when the operator wants the full picture, one prompt expands it; when they're done, it auto-reverts so the byline doesn't camp.

Eval

Shape-gate:

• state/log/byline-view.json exists with view: "agents" after invocation.
• set_at parses as ISO timestamp within last 60s.
• Statusline render contains the agents-detail header line.

Score = 1 if all three pass; else 0. Append to state/log/evals.ndjson with skill: "snappy-agents", verb: "set-view".

Gotchas

• 5-min auto-revert is enforced by statusline.sh on every render - no cron

needed.

• Multiple slash invocations within 5 min just refresh set_at; the view

doesn't toggle off. Use /snappy-default to clear before 5 min.

• Future views (/snappy-loop, /snappy-skills, etc.) write the same file

with a different view: value. Adding a new view = one elif in state/bin/statusline.sh plus a sibling skill.

Rubric

criteria:
  - name: byline_view_file_exists
    kind: deterministic
    check: "The file 'state/log/byline-view.json' must exist after skill execution."
  - name: byline_view_content
    kind: deterministic
    check: "The 'state/log/byline-view.json' file must contain '{'view':'agents', ...}' and 'set_at' must be a valid ISO 8601 timestamp within the last 60 seconds."
  - name: statusline_output_agents_view
    kind: judge
    check: "The rendered output from 'bash $HOME/projects/snappy-os/state/bin/statusline.sh' must clearly indicate the agents-detail view (e.g., specific header line)."
  - name: operator_notification
    kind: judge
    check: "The operator must be explicitly informed that the view is set, it auto-reverts in 5 minutes, and '/snappy-default' reverts sooner."

snappy-agents - loader

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

Critical Rules

• 5-min auto-revert is enforced by statusline.sh on every render - no cron

Commands

| ui dashboard | state/skills/snappy-agents/resources/ui.openui | |invoke: see state/skills/snappy-agents/SKILL.md Steps section |eval log: state/log/evals.ndjson (skill: "snappy-agents")

Self-Test

An agent reading this should correctly:

1. [ ] Know which lib/bin artifact backs this skill (or that it is prose-only)
2. [ ] Know what to write to state/log/evals.ndjson after invoking
3. [ ] Know the eval mode (auto / shape / manual) from the .md frontmatter

Self-report

If this loader fell short, append a line:

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

OpenUI Resource

• Skill-owned OpenUI Lang resource: state/skills/snappy-agents/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.