Gsd-skill-creator gupp-propulsion
Interrupt controller converting polled to proactive agent execution. Per-runtime strategies, configurable thresholds, Deacon heartbeat supervision. Fights LLM passivity bias.
git clone https://github.com/Tibsfox/gsd-skill-creator
T=$(mktemp -d) && git clone --depth=1 https://github.com/Tibsfox/gsd-skill-creator "$T" && mkdir -p ~/.claude/skills && cp -r "$T/project-claude/skills/gupp-propulsion" ~/.claude/skills/tibsfox-gsd-skill-creator-gupp-propulsion-ffc562 && rm -rf "$T"
project-claude/skills/gupp-propulsion/SKILL.mdGUPP Propulsion
The Gas Town Universal Propulsion Principle: If there is work on your hook, YOU MUST RUN IT.
GUPP is the interrupt controller of the Gastown chipset. In a real processor, the interrupt controller converts external events (keyboard press, network packet, timer tick) into CPU interrupts that force immediate handling. GUPP does the same for AI coding agents: it converts the polled model (agent checks periodically, waits for user input) into an interrupt-driven model (work appears on hook, agent executes immediately).
Why GUPP Exists
RLHF-trained LLM assistants have a strong bias toward waiting for the user — asking clarifying questions, seeking confirmation, pausing for feedback. This is appropriate in interactive chat but catastrophic for autonomous multi-agent orchestration, where every moment of idle waiting stalls the pipeline. Gastown discovered this empirically: agents spawned with a work item would introduce themselves, summarize the task, and wait, asking "Shall I proceed?" when the answer was already on their hook. GUPP overrides this trained passivity with an explicit, non-negotiable execution mandate: if you have hooked work, you do not wait, do not ask for confirmation, do not pause for feedback. You begin immediately. This is physics, not politeness.
Activation Triggers
This skill activates when:
- An agent has work assigned to its hook and is not yet executing
- Stall detection identifies an agent with hooked work that has gone idle
- A new agent is spawned and needs GUPP enforcement injected into its context
- Runtime-specific GUPP strategy selection is needed
- Heartbeat supervision needs to be configured for active agents
- An agent has been nudged but remains stalled
Enforcement at a Glance
GUPP enforcement adapts to each runtime via the Runtime HAL. The HAL exposes
getGUPPStrategy() which returns one of:
— Claude Code (SessionStart hook, highest fidelity)hook_injection
— Codex (tmuxstartup_fallback
, medium fidelity)gt prime
— Gemini / Cursor / unknown (prompt preamble + state polling)polling
A Deacon heartbeat loop runs inside the witness-observer at the configured
nudge_interval, detecting agents that received hooks but stalled. After restart_threshold, the watchdog requests a session restart. Per-runtime strategy tables, configurable thresholds, and the full heartbeat protocol are in references/runtime-strategies.md.
Safety Boundaries
These safety rules MUST remain in effect at all times — they are not advisory.
GUPP Is Advisory in GSD
GUPP enforcement is ADVISORY within GSD's structured workflow. The GSD orchestrator's phase gates, verification steps, and checkpoint protocols take precedence over GUPP urgency. If a GSD checkpoint requires human verification, GUPP does not override it. If a phase gate blocks progress pending approval, GUPP does not force execution past the gate.
The hierarchy is:
GSD orchestrator (highest authority) -> Phase gates and checkpoints -> GUPP propulsion (execution enforcement) -> Agent autonomy (lowest -- must obey all above)
GUPP operates between the orchestrator's structural gates. Within a phase, within an approved plan, within a committed task — GUPP demands immediate execution. But it never overrides the orchestrator's decision about what to execute or when a phase is complete.
Restart Limits
The watchdog restart mechanism has strict limits to prevent infinite restart loops:
| Limit | Value |
|---|---|
| Max restart threshold | 1800s (30 min, hard cap) |
| Max restarts per bead | 3 |
| Restart cooldown | 60s minimum between consecutive restarts |
After 3 restarts for the same work item, escalation to human is mandatory.
Human Escalation
After 3 restarts for the same bead without resolution, GUPP stops attempting automated recovery and escalates to a human operator via durable mail to the mayor. The mayor surfaces this through whatever channel the human is monitoring. GUPP does not attempt a fourth restart.
No Data Destruction
GUPP enforcement never destroys work in progress. Restarts preserve the agent's branch and commits. Nudges are non-destructive signals. Escalations are informational. At no point does GUPP delete files, reset branches, or discard uncommitted changes.
Integration with Other Gastown Skills
Reads runtime capabilities from
runtime-hal (getGUPPStrategy(), thresholds, restart support). Targets polecat-worker (the primary enforcement target). Runs inside witness-observer (Deacon heartbeat). Sends nudges via nudge-sync and escalations via mail-async. Reads agent activity timestamps from beads-state and hook status from hook-persistence. mayor-coordinator receives escalations. sling-dispatch sets hooks that activate GUPP enforcement.
References
Implementation detail moved to:
— per-runtime enforcement tables (Claude Code, Codex, Gemini, Cursor), threshold reference, Deacon heartbeat pattern.references/runtime-strategies.md
— observable metrics (response time, nudge effectiveness, strategy success, stall frequency) and the learning feedback loop.references/metrics-and-learning.md
— the GUPP principle from Gastown, how it fights model training bias.references/gastown-origin.md
— Deacon heartbeat supervision pattern and integration points.heartbeat.md