capacity
Show usage, limits and reset times for every signed-in AI account (Claude, Codex, Grok) as a card in chat, or a table in a terminal.
Skill by indigoai-us
Chalk Labs
Need help deploying capacity?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/indigoai-us-capacity
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/capacity
Tools it pre-approves 4
From allowed-tools in SKILL.md: the agent may use these without asking you each time.
Bash(hqcapacity:*),mcp__visualize__read_me,mcp__visualize__show_widget
What's inside
- Skill name
capacity- Description
- Show usage, limits and reset times for every signed-in AI account (Claude, Codex, Grok) as a card in chat, or a table in a terminal.
- License
- MIT
- Allowed tools
- Bash(hq, capacity:*),, mcp__visualize__read_me,, mcp__visualize__show_widget
- Instructions
- 56 lines in SKILL.md · view on GitHub
Before installing
- Pre-approves some shell commands
Files (2)
- SKILL.md
- openai.yaml · agents/
SKILL.md (first lines)
# /capacity Use this when the user says `/capacity` or asks to see AI account usage. Show usage, limits, and reset times for every signed-in AI account (Claude, Codex, Grok). The card comes from `hq capacity`. This skill never reads credentials, Keychain items, or provider APIs. ## Step 1: Ask hq for the card ```bash hq capacity --widget ``` Keep stdout as the fragment. Note the exit code. Do not pass `--json` with `--widget` (that is a usage error). Stop with one step, `hq capacity enable`, when either of these is true: - `hq` is not on PATH. - The command exits 0 and the fragment says capacity is not enabled or collection is off. Do not render a usage card and do not write the attention sentences in that case. If the widget tool from Step 2 is available and the fragment is that short not-enabled message, pass the fragment through unchanged and then stop. Otherwise print `hq capacity enable` and stop. When `--widget` is an unknown option, or `capacity` is an unknown command, this hq-cli is too old. Say once that `npm i -g @indigoai-us/hq-cli@latest` adds the card. If `hq capacity` itself runs, show its table (Step 3) and stop. If `capacity` is unknown, stop after the install line. Do not invent a table. Exit 0 with an HTML fragment means the ledger rendered. Go to Step 2 when `mcp__visualize__show_widget` is available. Otherwise go to Step 3. ## Step 2: Render the card 1. Call `mcp__visualize__read_me` once, silently, before the widget. Do not print its result. 2. Call `mcp__visualize__show_widget` with `widget_code` set to the fragment exactly as `hq capacity --widget` printed it, and `title` set to `ai_account_capacity`. 3. Do not edit the fragment. Do not recompute or retype any number in it. 4. After the card, write at most 3 short plain sentences. Name only what needs attention: a used-up limit, the account with the most headroom, and the next reset that matters. Use the card's own labels. Do not restate a percent, a count, or a clock time. If nothing needs attention, write nothing after the card. The card's Refresh button sends `/capacity`, which runs this skill again. ## Step 3: Terminal table Use this when `mcp__visualize__show_widget` is not available (terminal Claude Code, Codex, Cursor), or when Step 1 found that `--widget` is unknown and `hq capacity` still runs: ```bash hq capacity ``` Show that table as printed. Do not paste the HTML fragment in its place. Do not recompute its numbers. ## Adding an account To add another signed-in account, point the user to `hq capacity login`. Do not log in from this skill. ## Rules - The only command is `hq capacity`. No credential files, no Keychain, no provider HTTP APIs. - `hq` missing, or capacity not enabled: `hq capacity enable`, then stop. - Refresh re-runs `/capacity`. - Do not change the fragment.
From indigoai-us/hq-pack-core-skills, MIT.
More from indigoai-us/hq-pack-core-skills
- 0.570score
daily-brief
indigoai-us
Build the user's Daily Brief across personal work and every permitted company.
SkillAFreshness: AClaude Code +9 - 0.565score
decision-desk
indigoai-us
The owner's decision desk for one /super-conductor link.
SkillAFreshness: AClaude Code +9 - 0.565score
architect
indigoai-us
Find shallow modules and propose deepening refactors, ranked with file refs; never edits code.
SkillAFreshness: AClaude Code +9 - 0.565score
conduct-join
indigoai-us
Join this already-running session to a /conduct session as one of its children, so the conductor can send it instructions and receive its reports.
SkillAFreshness: AClaude Code +9 - 0.561score
codebase-design
indigoai-us
Vocabulary for designing deep modules and clean interfaces.
SkillAFreshness: AClaude Code +9 - 0.561score
conduct
indigoai-us
Orchestrator mode: coordinate only; small tasks go to subagents, worker areas to standing hq lanes.
SkillAFreshness: AClaude Code +9 - 0.558score
adr
indigoai-us
Capture qualifying architecture decisions as ADRs in the right HQ or repo location.
SkillAFreshness: AClaude Code +9 - 0.558score
accept
indigoai-us
Accept HQ membership invites from a magic link or raw token.
SkillAFreshness: AClaude Code +9 - 0.558score
commit-main
indigoai-us
Commit every dirty file in the current repo, only when on main.
SkillAFreshness: AClaude Code +9 - 0.558score
decision-queue
indigoai-us
Resolve pending user decisions one at a time, one picker per item.
SkillAFreshness: AClaude Code +9 - 0.558score
clean-worktree
indigoai-us
Merge an HQ worktree branch back into local main, then remove the worktree and branch.
SkillAFreshness: AClaude Code +9 - 0.558score
convert-codex
indigoai-us
Add Codex support to older Claude-first HQ roots without breaking Claude setup.
SkillAFreshness: AClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Oct 23, 2026 (7 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from indigoai-us
- 0.570score
daily-brief
indigoai-us
Build the user's Daily Brief across personal work and every permitted company.
SkillAFreshness: AClaude Code +9 - 0.565score
conduct-join
indigoai-us
Join this already-running session to a /conduct session as one of its children, so the conductor can send it instructions and receive its reports.
SkillAFreshness: AClaude Code +9 - 0.565score
architect
indigoai-us
Find shallow modules and propose deepening refactors, ranked with file refs; never edits code.
SkillAFreshness: AClaude Code +9 - 0.565score
decision-desk
indigoai-us
The owner's decision desk for one /super-conductor link.
SkillAFreshness: AClaude Code +9 - 0.561score
codebase-design
indigoai-us
Vocabulary for designing deep modules and clean interfaces.
SkillAFreshness: AClaude Code +9 - 0.561score
conduct
indigoai-us
Orchestrator mode: coordinate only; small tasks go to subagents, worker areas to standing hq lanes.
SkillAFreshness: AClaude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get capacity running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
capacity skill. Agent Mart. https://agentmart.dev/skills/indigoai-us-capacity (last updated 2026-10-24)