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 commands/nguyenthienthanh/aura-frog/plan-freezeWrote 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/commands/nguyenthienthanh/aura-frog/plan-freeze)<a href="https://agentmods.dev/commands/nguyenthienthanh/aura-frog/plan-freeze"><img src="https://agentmods.dev/badge/commands/nguyenthienthanh/aura-frog/plan-freeze.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00000 | $0.00358 |
| Opus 5 | $0.00000 | $0.00179 |
| Sonnet 5 | $0.00000 | $0.00072 |
| Haiku 4.5 | $0.00000 | $0.00036 |
Grade A, and why
plan-freeze 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 8d 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
/aura-frog:plan-freeze
Manually freeze a plan node, cascading to descendants. Alias for /aura-frog:plan freeze <id> (v3.7.2+).
Usage
/aura-frog:plan-freeze <NODE_ID> --reason "<text>"
/aura-frog:plan-freeze <NODE_ID> --conflict <CONFLICT-ID>
/aura-frog:plan-freeze --active --reason "..."
Delegation
bash aura-frog/scripts/plans/freeze-branch.sh <ID> [--reason "..."] [--conflict <CID>] [--force]
The script:
- Refuses on
done|archived|frozen. - Walks descendants depth-first (per Tech Spec §13.1 — descendants only, NOT siblings, NOT ancestors).
- Saves a checkpoint per touched node.
- Sets
status: frozen+freeze_reason+frozen_aton target; addsfrozen_by_ancestor: <NODE_ID>on descendants. - Optional
conflict_idlinks the freeze to a record inconflicts.jsonl. - Appends
history.jsonl event=freezewith cascade list.
--active resolves to active.task via resolve-node.sh --active.
Companion: /aura-frog:plan thaw (reverse), /aura-frog:plan conflicts list (find blocker IDs).
Full protocol in commands/plan.md.
Deprecation timeline: soft-deprecated v3.7.2, warning v4.0, removed v5.0.
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.
- 8d ago First seen · 36 lines · 0 tokens per session scan A 484a5ed108c9
plan-freeze is a command published in the GitHub repository nguyenthienthanh/aura-frog (24 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 358 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 2026-08-30.
Other commands, from other repositories
end-work
Complete work session with final checklist.
sync-linear
Sync current work with Linear ticket status.
status
The state of play, computed fresh: branch, dirty files, the active sprint, open work, index freshness.
feature
Role: Per-feature quality pipeline that takes a story or feature description from zero to a committed, documented, tested, and evaluated implementation. No stage is skipped. No commit happens without the evaluator's approval.
swarm
You are the Swarm Coordination Manager: a disciplined parallel execution engine that decomposes work into independent units, dispatches them to isolated workers, monitors progress, detects conflicts, and aggregates results into a coherent whole. You turn serial bottlenecks into parallel throughput — safely.
blueprint
A command for discussing and maintaining confirmed product requirements in one shared product blueprint.