capacity

A command that collects current usage percentages from Claude, Gemini, and Codex command-line tools.

In plain words
What is it for?
Use it when deciding which coding agent should handle a task based on Claude's session usage, Gemini's remaining usage, and Codex's five-hour and weekly limits.
Why use it?
It makes remaining usage visible so delegation decisions can account for each tool's available capacity.

Command

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.

agentmods
npx agentmods add commands/joshidikshant/devsquad/capacity
Clone the repo
git clone --depth 1 https://github.com/joshidikshant/devsquad
Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 555 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00011 $0.00555
Opus 5 $0.00005 $0.00278
Sonnet 5 $0.00002 $0.00111
Haiku 4.5 $0.00001 $0.00056

Measured yesterday against content hash 4766cf5f6875, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

capacity 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 yesterday.

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.

plugin/commands/capacity.md · 61 lines

What it actually says

DevSquad Capacity Report

Report your current CLI usage so DevSquad can make intelligent delegation decisions.

Instructions

Use AskUserQuestion to collect the user's current usage percentages. Explain how to check each one:

Ask the user these questions using AskUserQuestion:

Question 1: Claude usage %

  • Header: "Claude %"
  • Tell the user: "Check Claude: run /status then look at the 'Current session' percentage"
  • Options: "0-25%", "25-50%", "50-75%", "75-100%"

Question 2: Gemini usage %

  • Header: "Gemini %"
  • Tell the user: "Check Gemini: run gemini then /stats, look at the primary model's 'Usage left' and subtract from 100"
  • Options: "0-25%", "25-50%", "50-75%", "75-100%"

Question 3: Codex 5hr usage %

  • Header: "Codex 5hr"
  • Tell the user: "Check Codex: run codex then /status, look at '5h limit' percentage left and subtract from 100"
  • Options: "0-25%", "25-50%", "50-75%", "75-100%"

Question 4: Codex weekly usage %

  • Header: "Codex weekly"
  • Tell the user: "From the same Codex /status, look at 'Weekly limit' percentage left and subtract from 100"
  • Options: "0-25%", "25-50%", "50-75%", "75-100%"

After collecting answers, map the ranges to midpoint values:

  • "0-25%" → 12
  • "25-50%" → 37
  • "50-75%" → 62
  • "75-100%" → 87

If user provides exact numbers via "Other", use those directly.

Then save the capacity data:

source "${CLAUDE_PLUGIN_ROOT}/lib/state.sh"
source "${CLAUDE_PLUGIN_ROOT}/lib/usage.sh"
init_state_dir
save_capacity <claude_pct> <gemini_pct> <codex_5hr_pct> <codex_weekly_pct>

After saving, run the status command to show the updated report:

bash "${CLAUDE_PLUGIN_ROOT}/skills/devsquad-status/scripts/show-status.sh"

Display the result to the user with the delegation recommendation.

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.

  1. yesterday First seen · 61 lines · 11 tokens per session scan A 4766cf5f6875

Subscribe to this mod's changes

capacity is a command published in the GitHub repository joshidikshant/devsquad (7 stars, last pushed 1mo ago), licensed MIT. It adds 11 tokens to every session and 555 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.