Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/nguyenthienthanh/aura-frognpx agentmods add skills/nguyenthienthanh/aura-frog/plan-orchestratorWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/nguyenthienthanh/aura-frog/plan-orchestrator)<a href="https://agentmods.dev/skills/nguyenthienthanh/aura-frog/plan-orchestrator"><img src="https://agentmods.dev/badge/skills/nguyenthienthanh/aura-frog/plan-orchestrator/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/nguyenthienthanh/aura-frog/plan-orchestrator"><img src="https://agentmods.dev/badge/skills/nguyenthienthanh/aura-frog/plan-orchestrator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00091 | $0.02809 |
| Opus 5 | $0.00046 | $0.01404 |
| Sonnet 5 | $0.00018 | $0.00562 |
| Haiku 4.5 | $0.00009 | $0.00281 |
Grade A, and why
plan-orchestrator 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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 211 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI-consumed reference. Optimized for Claude to read during execution. Human-readable explanation: see docs/architecture/HIERARCHICAL_PLANNING.md or docs/getting-started/ depending on topic.
Plan Orchestrator
Single entry point for the 11-verb hierarchical-planning vocabulary. Routes user intent → backing script in aura-frog/scripts/plans/. Replaces 10 separate command files with one consolidated dispatcher.
Owner command: commands/plan.md (single user-facing command)
Bare-word router: hooks/bare-word-router.cjs (active-plan vocabulary)
Data model: .claude/plans/ per Tech Spec §6
verb_table[11]
verbs[11]{verb,tier_in,tier_out,script,mutates_active_json}:
bootstrap,—,T0+T1+T2,new-plan.sh,true
expand,T1/T2/T3,T2/T3/T4,expand-node.sh,false
next,T3,T4,next-task.sh,true
status,—,—,render-plan-tree.sh,false
replan,T1-T4,T1-T4,replan-node.sh,false
promote,T4,T1/T2,promote-node.sh,false
archive,T2+,T2+,archive-feature.sh,false
undo,T1-T4,T1-T4,undo-decision.sh,true
freeze,T1-T4,T1-T4,freeze-branch.sh,false
thaw,T1-T4,T1-T4,thaw-branch.sh,false
conflicts,—,—,conflicts-scan.sh,false
bootstrap is the unprefixed /aura-frog:plan (no verb) — T0/T1/T2 interview. Every other verb requires an explicit target node ID or option flags.
intent_keywords[11]
Used by Stage 2 of the routing pipeline when the user's input has no explicit verb prefix. Match by stemmed substring (case-insensitive).
keywords[11]{verb,phrases}:
bootstrap,"plan|bootstrap|set up the plan|init plan|new plan"
expand,"expand|decompose|break down|drill down|split into stories|split into tasks"
next,"next|next task|what's next|claim next|dispatch next|pick up"
status,"status|tree|render|show plan|where are we|progress"
replan,"replan|rework|reset|redo plan|discard plan|change plan"
promote,"promote|surface|bubble up|elevate|discovery|insight up"
archive,"archive|compress|wrap up|finalize feature|close out"
undo,"undo|rollback|revert|restore|step back"
freeze,"freeze|pause|halt|park|block|stop work on"
thaw,"thaw|unfreeze|resume|continue|unblock"
conflicts,"conflict|collision|overlap|incompatible|conflicts list|conflict check"
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.
- 5d ago First seen · 211 lines · 91 tokens per session scan A 3c8ec70147de
plan-orchestrator is a skill published in the GitHub repository nguyenthienthanh/aura-frog (24 stars, last pushed 4d ago), licensed MIT. It adds 91 tokens to every session and 2,809 once invoked, about $0.0005 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 2026-09-03.
Other skills, from other repositories
resume_handoff
Resume work from handoff document with context analysis and validation.
create_handoff
Create handoff document for transferring work to another session.
feature
Deliver a feature or chore end to end, from branch creation to PR readiness, starting from an issue URL or a plain description.
gsd-manager
Interactive command center for managing multiple phases from one terminal.
gsd-new-project
Initialize a new project with deep context gathering and PROJECT.md.
gsd-resume-work
Resume work from previous session with full context restoration.