A command that estimates the Phoenix high-performance computing charge for a CPU or GPU job. Phoenix is a computing cluster; the estimate uses the resource type, running time, optional service tier, and optional hourly rate.

Use it with GPU or CPU type and hours, or answer its questions in a wizard, to estimate billed usage or a dollar amount.

It avoids doing the charge calculation by hand and explains when a job has no charge.

pace-cost — Command for Claude Code by HCAI-Lab-GT

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.

Clone the repo

git clone --depth 1 https://github.com/HCAI-Lab-GT/gt-hive

Made for: Claude Code.

Or install gt-hive-pace, the plugin that ships this one along with the rest of its 3 skills, 3 commands, 1 hook.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/hcai-lab-gt/gt-hive/pace-cost/github.svg)](https://agentmods.dev/commands/hcai-lab-gt/gt-hive/pace-cost)

Your own site

<a href="https://agentmods.dev/commands/hcai-lab-gt/gt-hive/pace-cost"><img src="https://agentmods.dev/badge/commands/hcai-lab-gt/gt-hive/pace-cost/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.

Your own site · 80×15

<a href="https://agentmods.dev/commands/hcai-lab-gt/gt-hive/pace-cost"><img src="https://agentmods.dev/badge/commands/hcai-lab-gt/gt-hive/pace-cost.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 821 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00025	$0.00821
Opus 5	$0.00013	$0.00411
Sonnet 5	$0.00005	$0.00164
Haiku 4.5	$0.00003	$0.00082

Measured 10d ago against content hash 2b27abd9e6f2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

pace-cost 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 10d 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.

claude/commands/pace-cost.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

cost estimator

Compute the Phoenix charge for a job. The command is a hybrid: it accepts positional arguments for fast use, and falls into a wizard if invoked with no arguments.

Step 1: parse the arguments

$ARGUMENTS is the user's invocation tail. Two cases:

Case A — $ARGUMENTS is non-empty. Parse it as <gpu-or-cpu> <hours> [qos] [rate]. Examples:

/gt-hive-pace:pace-cost h100 4 -> 1× H100, 4 hours, default QOS, no rate supplied (returns billed usage hours only).
/gt-hive-pace:pace-cost cpu 24 embers -> CPU job, 24 hours, free embers QOS (always $0).
/gt-hive-pace:pace-cost h200 0.5 inferno 2.50 -> 1× H200, 30 minutes (fractional hours are supported), paid QOS, $2.50/GPU-hour user-supplied rate.

If the args do not parse, ask the user to clarify and skip to Case B.

Case B — $ARGUMENTS is empty. Use AskUserQuestion to collect four inputs: resource (GPU type or CPU), hours (fractional allowed), QOS (inferno paid / embers free / unsure), and optional per-hour rate.

Step 2: redirect ICE callers

If the user mentions ICE, the answer is one line: ICE jobs are free — there is no charge model and no estimator. Stop.

Step 3: load `pace-phoenix` and read the cost model

Load the pace-phoenix skill. Read pace-phoenix/references/cost-model.md for the cost formula (usage-hours = (resource count) * (walltime hours), estimated cost = usage-hours * user-supplied rate), the inferno paid vs embers free rules, and the --rate-cpu-hour / --rate-gpu-hour inputs the model expects.

The cost model intentionally externalizes hourly rates because PACE pricing changes; do not hard-code a rate. The user must supply one (in $ARGUMENTS or via the wizard) or this command falls back to usage-hours only.

Step 4: compute and report

Compute usage hours from the cost-model formula. Two cases for the report:

With a user-supplied rate: estimate = usage-hours * rate. Report:

Estimate: $X.XX for h on (QOS: , rate $/h).

: embers is free; inferno is paid against your gts-* charge account.

Rates change. If accuracy matters, re-check cost-model.md and pace-quota on the cluster.

Read the full file on GitHub · 78 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.

10d ago First seen · 78 lines · 25 tokens per session scan A 2b27abd9e6f2

Subscribe to this mod's changes

pace-cost is a command published in the GitHub repository HCAI-Lab-GT/gt-hive (4 stars, last pushed 1mo ago), licensed MIT. It adds 25 tokens to every session and 821 once invoked, about $0.0001 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.

Scientific

verify-math

Verify a self-authored mathematical result end to end by routing claims across adversarial review, numerical falsification, symbolic or CAS checks, and Lean, then aggregating one report. Use when a theorem, proposition, conjecture, or paper-wide mathematical argument needs the appropriate combination of verification…

flonat/flonat-research · 81 tokens

pace-cost

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

cost estimator

Step 1: parse the arguments

Step 2: redirect ICE callers

Step 3: load `pace-phoenix` and read the cost model

Step 4: compute and report

What this file has done since we first saw it

Other commands, from other repositories

verify-math

replication-package

diff

simulation-calibrator

arg-diagram

graphite-morphology-classify

pace-cost

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

cost estimator

Step 1: parse the arguments

Step 2: redirect ICE callers

Step 3: load pace-phoenix and read the cost model

Step 4: compute and report

What this file has done since we first saw it

Other commands, from other repositories

verify-math

replication-package

diff

simulation-calibrator

arg-diagram

graphite-morphology-classify

Step 3: load `pace-phoenix` and read the cost model