liveness-discipline

Rules for running long or quiet tasks without losing track of whether they are progressing. These tasks can include scripts, deployments, downloads, browser automation, or other agents.

In plain words
What is it for?
It helps set safe time limits, monitor progress, diagnose apparent hangs, and ensure long-running work produces a completion signal.
Why use it?
A task that hangs without reporting completion can leave the system waiting indefinitely and make an idle task look finished.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/fusebase-dev/fusebase-flow/liveness-discipline
Any agent
npx skills add fusebase-dev/fusebase-flow --skill liveness-discipline
Clone the repo
git clone --depth 1 https://github.com/fusebase-dev/fusebase-flow

Made for: Claude Code, Codex.

Per session 176 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,512 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00176 $0.03512
Opus 5 $0.00088 $0.01756
Sonnet 5 $0.00035 $0.00702
Haiku 4.5 $0.00018 $0.00351

Measured 2d ago against content hash c5b50984fe8a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

liveness-discipline scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.agents/skills/liveness-discipline/SKILL.md · 139 lines

How it starts

The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Liveness Discipline (FR-27)

The failure (why this rule exists)

A long/silent command (probe, test script, deploy, fetch loop, browser automation), a sub-agent, or a harness-auto-backgrounded workflow that HANGS emits no completion event. The host therefore never re-invokes the agent, which idles indefinitely while appearing "done" — until a human asks "is it still running?". The hang→no-event→idle failure is invisible by construction: there is no elapsed-time/idle event in the hook schema, and a call that never returns can never fire a post-call hook. So this rule is not enforced by a gate or a verification hook — a Stop-time "watchdog: applied" signal would be attestation theatre. Enforcement = safe-default tooling (hooks/local/lib/bounded-run.sh) + present-by-construction delivery (this skill in context at launch time).

Guardrail (the rule's floor)

Quality/safety floor unchanged. Never launch bare — but a liveness guarantee is the floor, not a license to kill a slow-but-progressing job. A bounded deadline is sized for the work, never so tight it trains premature kills (the FR-26 "budget gate trains truncation" lesson, inverse). Diagnose before you kill.

Protocol — never launch bare → attach ≥1 liveness guarantee

Before launching ANY long/silent work, attach at least one of these. In preference order:

# Guarantee When How
1 Complete in-turn the work fits the current turn run foreground with a hard timeout; do not background it at all
2 Bounded wrapper + incremental logging the work is genuinely long and you must background it source hooks/local/lib/bounded-run.sh + one bounded_run call (below); the wrapper emits a terminal timeout line so the job reaches completion-or-death, never a silent idle
3 BLOCKED-AT-<gate> + record-then-read pointer the remaining wait is UNBOUNDED (human approval gate, external event with no ETA) return the explicit BLOCKED-AT-<gate> verdict + what "cleared" looks like + a pointer to where reality is recorded; the orchestrator re-dispatches when the gate clears (flow-skills/task-delegation Blocked-return rule)

Read the full file on GitHub · 139 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 139 lines · 0 tokens per session scan A c5b50984fe8a

Subscribe to this mod's changes

liveness-discipline is a skill published in the GitHub repository fusebase-dev/fusebase-flow (9 stars, last pushed 7d ago), licensed MIT. It adds 176 tokens to every session and 3,512 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

adobe-express-core

Adobe Express environment essentials, two-runtime architecture, project setup, and MCP server configuration. Use when starting add-on development, understanding iframe vs sandbox boundaries, configuring MCP servers, setting up local projects, or validating manifest configuration.

Sandgrouse/adobe-express-dev-skill · 50 tokens

adobe-express-monetization

Monetize Adobe Express add-ons with subscriptions and payments. Use when designing checkout flows, defining subscription tiers, implementing webhook verification, managing entitlements, or securing backend billing logic.

Sandgrouse/adobe-express-dev-skill · 44 tokens

adobe-express-spectrum-ui-ux

Build or review Adobe Express add-on panel UI with Spectrum patterns, stack selection guidance (raw SWC, swc-react, React Spectrum), Express theme setup, state and navigation design, and actionable UX quality checks. Use when implementing or auditing panel layouts, interaction states, multi-screen flows, and…

Sandgrouse/adobe-express-dev-skill · 70 tokens

adobe-express-cors-and-backend

Diagnose and fix CORS errors between Adobe Express add-on UI and backend APIs across local development, private listing, and public listing stages. Use when browser requests fail with preflight, Access-Control-Allow-Origin, Access-Control-Allow-Headers, or OPTIONS issues; when moving from localhost to hosted add-on…

Sandgrouse/adobe-express-dev-skill · 92 tokens

adobe-express-document-manipulation

Create and modify document content in Adobe Express add-ons using Document SDK. Use when planning document operations, inserting shapes/text/media, sequencing sandbox commands, or troubleshooting document edits.

Sandgrouse/adobe-express-dev-skill · 43 tokens

adobe-express-oauth-authentication

Implement OAuth 2.0 and authentication flows for Adobe Express add-ons. Use when connecting to cloud providers (Dropbox, OneDrive, Google Drive), managing tokens, storing credentials, or designing login surfaces.

Sandgrouse/adobe-express-dev-skill · 50 tokens