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.
npx agentmods add commands/vmobifystudio/app-dev-team/app-manager-failovergit clone --depth 1 https://github.com/vmobifystudio/app-dev-teamWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00000 | $0.00116 |
| Opus 5 | $0.00000 | $0.00058 |
| Sonnet 5 | $0.00000 | $0.00023 |
| Haiku 4.5 | $0.00000 | $0.00012 |
Grade A, and why
app-manager-failover scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
/app-manager-failover — recover manager ownership
Before respawning or replacing a manager, inspect its durable lease:
node "${CLAUDE_PLUGIN_ROOT}/scripts/manager-failover.mjs" \
--ledger "$RUN_LEDGER" --run <run-id> --manager tech-manager --backup tech-lead
HOLD means the primary lease is still active and a second manager must not start. FAILOVER
means the lease is absent or expired. BLOCK means duplicate active manager attempts require
operator review.
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.
- 2d ago First seen · 13 lines · 0 tokens per session scan A 752c82bbdedf
app-manager-failover is a command published in the GitHub repository vmobifystudio/app-dev-team (4 stars, last pushed 23d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 116 tokens. 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.
Other commands, from other repositories
analyze-cluster-postmortem
Postmortem analysis of cluster failures → OPTIMIZE PROMPTS to work for EVERY use case.
context
Analyze and optimize context configuration. Reviews CLAUDE.md, knowledge-core.md, and active context for optimization opportunities. Helps prevent context rot (39% improvement, 84% token reduction).
parallel-task
Executes a structured plan in parallel waves, spawning appropriate agents for each task based on dependencies and confidence routing.
handoff
Create a model handoff using a single canonical handoff document and then validate it.
elite-orchestrate
You MUST start your FIRST response with this exact agent activation line.
onboard
Detect the project stack and draft a repo-appropriate CLAUDE.md (language, framework, test runner, lint setup, agents and commands that fit).