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/nguyenthienthanh/aura-frog/rungit clone --depth 1 https://github.com/nguyenthienthanh/aura-frogWrote 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/run)<a href="https://agentmods.dev/commands/nguyenthienthanh/aura-frog/run"><img src="https://agentmods.dev/badge/commands/nguyenthienthanh/aura-frog/run.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 | $0.00000 | $0.02353 |
| Opus 5 | $0.00000 | $0.01177 |
| Sonnet 5 | $0.00000 | $0.00471 |
| Haiku 4.5 | $0.00000 | $0.00235 |
Grade A, and why
run 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 4d 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 — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Run Commands
The universal entry point. Type /run <task> and Aura Frog auto-detects intent: feature, bugfix, refactor, test, deploy, review — then runs the right flow.
Category: Core Scope: Session
EXECUTION PROTOCOL — FOLLOW IN ORDER
When the user types /run <task>, Claude MUST execute these steps in order. Do NOT skip ahead to implementation.
- Read
skills/run-orchestrator/SKILL.mdfully. That skill carries the playbook. This command file is documentation about /run, not the playbook itself. - Run agent-detector to classify complexity (Quick / Standard / Deep / Project) and pick the flow per the detection table below.
- Escalation check (v3.7.2+) — Before creating the run state, evaluate the escalation heuristic from
rules/workflow/run-plan-bridge.md. If the task scores weight ≥ 3 AND no plan tree exists, emit the 3-option prompt (plan/deep/details). Seeskills/run-orchestrator/SKILL.mdStep 0 for full semantics. Override prefixes:/run task: <desc>— force task mode (Quick/Standard/Deep), skip escalation./run project: <desc>— force project mode; write.claude/cache/pending-plan-bootstrap.jsonand invoke/aura-frog:plandirectly.AF_ESCALATION_DISABLED=true— opts out per-session.
- Create the run state file at
.claude/logs/runs/<run-id>/run-state.jsonperskills/run-orchestrator/SKILL.mdStep 0b. MANDATORY — do not proceed without it. If escalation ran and the user pickeddeep, recordescalation_declined: truein run-state. - Apply the Run ↔ Plan bridge (
rules/workflow/run-plan-bridge.md):.claude/plans/active.json#active.taskset → auto-anchor; deliverables sync back to the plan tree on Phase 5.- Active feature without claimed task → suggest
/aura-frog:plan next. - No plan + escalation prompt was emitted in Step 3 (the trigger heuristic owns this case now).
AF_RUN_PLAN_BRIDGE_DISABLED=truedisables the bridge entirely (also disables Step 3 escalation).
- Announce the chosen flow to the user transparently: "Detected: Standard → single-agent inline (no plan). Say
deepto escalate." When anchored, also state the anchor: "Anchored to TASK-00101 (story STORY-0042, feature FEAT-A)." - Then execute the chosen flow. For Deep, follow the 5-phase workflow in run-orchestrator. For Standard/Quick, lighter flow per the table. For Project (escalated via Step 3), the run handed off to
/aura-frog:planand this invocation terminates.
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.
- 4d ago First seen · 164 lines · 0 tokens per session scan A 5171499c2dbb
run is a command published in the GitHub repository nguyenthienthanh/aura-frog (24 stars, last pushed 10d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,353 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
review-agentready
AgentReady-specific code review with attribute mapping and score impact analysis.
speckit.specify
Create or update the feature specification from a natural language feature description.
speckit.checklist
Generate a custom checklist for the current feature based on user requirements.
speckit.implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
speckit.tasks
Generate an actionable, dependency-ordered tasks.md for the feature based on available design artifacts.
speckit.clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.