Your coding agents check their Claude and Codex limits before they start a job.
headroomd reads the 5-hour and weekly limits your subscriptions report and answers go, wait or reroute, over the CLI or MCP.
npm install -g headroomd # or: brew install apertur3/tap/headroom
headroom setup
headroom can claude-fable --owner me && echo go
Then install the Claude Code plugin (requires headroomd above):
claude plugin marketplace add Apertur3/headroom
claude plugin install headroom@headroom
Fuel gauge for AI coding agents: reads real plan limits, answers go, wait or reroute.
星數
15
工具
—
可用率
—
macOS, Linux, Windows (experimental). No telemetry. Zero runtime dependencies.
Not related to headroomlabs-ai/headroom, the context-compression project.
Install
Node 22.13 or newer. The npm package is headroomd; the Homebrew formula is
apertur3/tap/headroom. Both install the headroom command.
npm install -g headroomd
# or, on macOS and Linux: brew install apertur3/tap/headroom
# finds your logins, runs the doctor, asks before each change
headroom setup
# one block per account: percent used, reset time and pace state per window
headroom
Claude usage comes from Claude Code's statusline. Add this to ~/.claude/settings.json (or the
settings.json of each other profile), or chain an existing statusline with
headroom statusline --chain '<your command>':
Alongside it, Headroom runs Claude Code's own /usage at most every 10 minutes (it adds the scoped meters the statusline does not carry; the statusline never
runs under claude -p, so it can go stale between runs). headroom doctor and headroom status say which is in
use. Headroom never edits your Claude settings files.
For Claude Code, install the plugin after installing headroomd with npm or Homebrew:
claude plugin marketplace add Apertur3/headroom
claude plugin install headroom@headroom
It bundles the Headroom skill, the MCP server registration and a quota line on every prompt.
Using it alongside headroom hook install does not print the quota line twice.
See Claude Code plugin for requirements and uninstall commands.
Already running Claude Code or another agent? Copy skills/headroom/SKILL.md into its skills directory and say "set up headroom".
Without the plugin, headroom setup offers to register the MCP server for your default Claude Code
profile. To register it by hand, or in another profile:
claude mcp add --scope user headroom -- headroom mcp
CLAUDE_CONFIG_DIR=~/.claude-work claude mcp add --scope user headroom -- headroom mcp
Agents without MCP, Codex for example, call the CLI. Then give your agents the instructions in
For agents. The MCP tools and example calls are in
docs/mcp-and-agents.md.
The three commands above are the short path. Discovery on its own:
headroom accounts discover # finds Claude, Codex, Antigravity, Grok and Kimi logins
On macOS and Linux, brew install apertur3/tap/headroom installs the same package and adds a
brew services start headroom service.
By hand, the same steps are one command:
headroom setup # discovery, doctor, service, MCP registration -- asks before each change
Run headroom notify configure to choose notification channels, a preset and overrides. Run
headroom update only when you choose to install a newer package; headroom uninstall reverses
setup, and headroom completion <bash|zsh|fish|pwsh> prints a shell completion script.
accounts discover prints what it wrote (Wrote ~/.headroom/accounts.toml (4 accounts). Next: headroom doctor) and, the first time, seeds ~/.headroom/policy.toml and routing.toml from examples/ so
headroom can <class> --owner <your-agent-name> works immediately with the example action classes (claude-fable, codex-build,
gemini-bulk) -- edit routing.toml to match your accounts.
Keep an optional second profile that is deliberately logged out without polling it: add
enabled = false to its [[accounts]] block, or run headroom accounts disable <name>.
It remains configured and can be restored with headroom accounts enable <name>.
Full walkthrough, including what each step grants and why: docs/quickstart.md.
status/doctor check the npm registry at most once a day (a plain GET of the headroomd
version, no account data) and print a one-line notice when a newer headroomd is out; run
headroom update (never automatic) to install it. Set update_check = false in
~/.headroom/policy.toml to turn the check off -- see
Staying up to date.
For agents
Paste this into the CLAUDE.md or AGENTS.md your agents read, and replace the placeholders with
your own action classes, meters and agent name. The agent then checks Headroom before it dispatches
work, instead of asking you.
## Usage limits (Headroom)
Check Headroom before you start work on a subscription. Do not ask me about usage or reset times.
- `headroom can <class> --owner <your-name>`: exit 0 means go, exit 2 means no. Any other exit
is an error: treat it as no. Classes are the `[consumes]` entries in `~/.headroom/routing.toml`.
- On no, try the next class in your fallback list. If none has room, run
`headroom wait --meter <meter> --until-reset --max 6h` (exit 3 means it timed out), then run
`headroom can` again before you start anything.
- Start a job with
`headroom run --meter <meter> --need <window>:<points> --owner <your-name> -- <command>`,
for example `--need 5h:10` for 10 percent of the 5-hour window. It reserves the points, runs
the command and releases them when it exits. Exit 2 means refused; otherwise it returns the
command's own exit code.
- UNKNOWN means there is no trustworthy reading. Treat it as no. Never pass `--allow-unknown`
unless I ask for it.
- For the full picture, read `headroom --json`, not the human view.
- In Claude Code with the Headroom MCP server, `quota_can` answers the same question as
`headroom can`.
To put live quota in front of the agent on every turn, run headroom hook install --agent claude
(or answer yes in headroom setup). Each Claude Code prompt then carries one line the daemon wrote at
its last poll, with its age, for about 60 tokens per turn; headroom line prints the same line for any
agent. Claude Code on macOS and Linux only for now; Windows, Codex and Gemini hooks are not supported yet.
A plain can is advisory. A reservation tells other agents that use Headroom the points are taken;
it does not limit what the job itself spends, and it cannot stop tools that do not use Headroom.
The longer version, with pace states, leases and reserves, is
skills/headroom/SKILL.md.
Platform support and known limitations
Tests
npm test (vitest), run on every push on macOS, Ubuntu and Windows; some tests are POSIX-only and skip on Windows. Current counts are in the CI logs; method and limits: docs/verification.md
CI platforms
macOS, Ubuntu and Windows (macos-latest, ubuntu-latest, windows-latest): lint, tests, build, npm pack --dry-run, privacy sweep, npm audit
Daily use
one macOS machine; this is the only environment a person uses every day
Install from the packed tarball
scripted cold-install smoke test (smoke-cold.sh) runs in the release workflow; also checked by hand on macOS and on Linux ARM64
Windows
experimental. On Windows 11, headroom install-service registers a "Headroom Daemon" task that starts immediately and serves a per-user named pipe whose name is a hash only. headroom uninstall --home asks the running daemon to shut down over that pipe, removes the task and the home, and exits 0. After an in-place upgrade, headroom install-service restarts the daemon onto the new version, except a daemon started by 0.2.6 or older, which has no shutdown request and must be stopped by hand once (end node.exe in Task Manager). Verified on Windows 11: MCP registration (claude mcp add --scope user headroom -- headroom mcp shows Connected) and a real Claude login read (fresh on the first poll). Not verified on Windows: a slow stop (the 27 second wait is covered by unit tests only) and start at logon and across reboots. Earlier, 0.2.4 was installed on Windows 11 and accounts discover, doctor, status / can / gate / dashboard (UNKNOWN, never a fake number) and the HTML report permissions worked. The process watchdog is inactive on Windows. PowerShell's default execution policy blocks the npm and headroom.ps1 shims; use cmd, or relax the policy
Works with
Claude Code through MCP (registered with claude mcp add, covered by mcp-registration.test.ts and daemon-mcp.test.ts); any agent that can run a shell command, through the CLI and --json. Other MCP clients: untested
Antigravity
experimental; macOS 14 or later only, and it depends on a private local endpoint that the vendor can change
Vendor endpoints
private and unversioned. Headroom pins them, records redacted fixtures and prints UNKNOWN when a shape changes, but it cannot promise they keep working
Why
An agent that fans out several jobs needs two answers first: can this account afford them, and
which other jobs have already reserved capacity? Vendor screens answer neither for a program, and
a stale reading can send more work to an account that no longer has capacity. Headroom combines
vendor readings with cooperative reservations. When a reading is stale or failed it says UNKNOWN
instead of a number, and can answers NO for it unless you pass --allow-unknown.
One daemon reads quota across Claude, Codex, Antigravity, Grok, Kimi, and local vLLM or llama.cpp
pools, keeps history, and detects resets. Antigravity and Grok support is experimental.
Demo
How it differs from a usage analyzer
Usage analyzers such as ccusage read local usage files and
report estimated costs. Headroom reads the usage and limits your vendors report, from their own
usage endpoints, and answers before work starts: can, gate, route, leases and an inbox, for
agents that dispatch work. They answer different questions and work side by side.
Before and after
Without a check, an agent finds the limit by hitting it, in the middle of a task. With Headroom it
checks first and tries the next class in your fallback list when the answer is NO. can only
checks; when several jobs start at once, use headroom run so each one reserves its capacity.
Without Headroom
# weekly limit reached mid-task, work stops half done
codex exec "refactor the billing module"
With Headroom
if headroom can codex-build --owner builder; then
codex exec "refactor the billing module"
elif headroom can claude-fable --owner builder; then
claude -p "refactor the billing module"
else
# no class has room: wait for a reset, then check again before dispatching
headroom wait --meter codex-main:main --until-reset --max 6h
fi
headroom run --meter ... --need ... --owner ... -- <command> goes one step further: it checks,
reserves the capacity for the job's duration so other agents that use Headroom see it as taken,
runs the command, and releases the reservation. Runnable examples against synthetic data are in examples/.
Features
Vendors and meters
Claude all, fable, routines and reported scoped meters; Codex main, spark, credits; Antigravity gemini, claude-gpt; Grok, Kimi; and local vLLM or llama.cpp capacity pools
Pace
HARVEST, NORMAL, CONSERVE, FREEZE or UNKNOWN per window, from a straight line burn with a grace period after each reset
Decisions
can, gate, route, plan, fill, wait, leases, per-meter reserves, and a spend ledger coordinate shared capacity and pacing
Views and automation
Terminal status, dashboard/top (and --html <path> browser report), statusline --render, usage --paste or --clipboard, JSON contract output, local daemon, and MCP tools
Operations
Interactive setup; the notify configure picker with calm, quiet and everything presets; inbox; export as JSON or CSV; doctor --bundle; update; uninstall; and shell completion
Headroom is not a router. Which model is good at what is your opinion and changes monthly. Keep it
in ~/.headroom/routing.toml; Headroom only filters your fallback list by budget. It also never sits in
the request path.
Use Tab to select a meter, v for details, and e for events. Both chart views show
recorded remaining capacity, with gaps where readings are missing or untrusted.
To open the same recorded history in a browser:
headroom dashboard --html report.html
Open the generated file in your browser. The report shows subscription usage and reset times in an overview, with selectable window charts and sample details. It supports light and dark themes and makes no external requests. It is a snapshot: generate it again for newer readings. Existing files are preserved unless you pass --force; new files use mode 0600 on systems that support Unix permissions.
Design principles
Each of these is a rule the code enforces and a test pins. Past real-world breakage is the reason for every one.
Fail closed: never a fake number. A missing, stale or inconsistent reading becomes UNKNOWN, and can answers NO for it unless you explicitly pass --allow-unknown.
A stale-lane canary that cannot be silenced. A lane with no fresh reading for 6 hours raises an alert, whatever the notification config says.
Only kill what Headroom provably started. On macOS and Linux, a process is signalled only if its recorded pid, command and start time still match.
Secrets stay in their own stores. Notification tokens live in the OS secret store; vendor credentials are read at use time from the vendor's own store or credential file and never copied. Output is redacted.
A redacted fixture per past breakage. Every Antigravity failure shape seen in the field has a fixture and a test.
A stale-lane canary that cannot be silenced and does not spam humans. A meter lane with no
fresh reading for 6 hours (configurable) raises an alert into the inbox and headroom doctor.
It runs before and independently of the notification config, so a muted channel or
events_off cannot hide it. External channels get nothing per lane; at most one plain-language
message per principal per episode, after 24 hours, held during quiet hours
(canary.ts, stale-lane-canary.test.ts).
Process hygiene: only kill what Headroom provably started. A process is signalled only if
recorded evidence (pid, command and start time from when Headroom launched it) still matches
the live process, re-checked immediately before every signal, so a recycled pid is never hit.
An age watchdog reaps Headroom-started agy processes that outlive their limit
(process-tree.ts, agy-watchdog.ts,
antigravity-keepalive-stop-recycled-pid.test.ts,
agy-watchdog.test.ts). The test suite itself fails if any
process it started outlives the run (global-leak-gate.ts). The
watchdog and the pid and start-time checks are not active on Windows.
Secrets stay in their own stores. Headroom's own credentials (notification tokens) are
read at use time from the macOS Keychain (secret-tool on Linux, Credential Manager on
Windows) and never written to disk; vendor tokens are read at call time from the vendor's own
store or credential file (for Kimi's manual token and the Moonshot key, a 0600 file you save
yourself) and dropped. Output and logs are redacted
(notify.ts, security.ts,
security.test.ts, SECURITY.md).
A redacted fixture per past breakage. Every Antigravity failure shape seen in the field
has a fixture (recorded and redacted, or synthetic) and a test that runs it through the real
code path (test/fixtures/antigravity/,
record-antigravity-fixture.sh). The repo
also scans itself and its packed npm tarball for private addresses, emails and home paths
(privacy-sweep.sh, run in CI).
How it fits together
Headroom reads Claude, Codex, Grok and Kimi through native TypeScript adapters.
Antigravity is experimental and supported on macOS 14 or later: it requires a logged-in
agy and a running Headroom daemon. The npm and Homebrew packages include a universal
macOS reader, verified by SHA-256 before use. Gemini CLI is not required or supported for consumer subscriptions;
Google ended consumer Gemini CLI access on June 18, 2026.
For Antigravity quota, the bundled macOS reader finds the running Antigravity language server
(the daemon-kept agy) in the process list, takes its local port and, where the process has one,
the local CSRF token from its command line, and asks that server on 127.0.0.1 for its quota
summary. It does not read agy's OAuth or session credential. The daemon also reads the tail of
agy's newest log under ~/.gemini/antigravity-cli/log for login-state markers only. Headroom never reads the Gemini CLI's OAuth file.
Missing or failed summaries stay UNKNOWN. An idle window with real fractions may carry
a doubt marker when its reset time looks synthetic. A five-hour window entirely absent
from an otherwise-successful response (a genuinely idle rolling window) prints n/a
instead of UNKNOWN and does not block a budget check. The endpoint contracts and native
reader build on CodexBar (MIT).
A budget check before a job
This synthetic example has 20% usage and another owner reserving 75%. The remaining capacity
cannot cover another 10-point job, so the child command never starts:
$ headroom run --meter claude-main:all --need wk:10 --owner builder -- codex exec "Run the tests"
wk needs 10 more but only 0.0 left after 75.0% already leased before the 10% reserve
When there is enough capacity, run reserves it, starts the command, and releases the reservation
when it finishes. The check and reservation are atomic across processes. A plain can or gate
is advisory; use run or can --lease when starting work. These reservations coordinate agents
that use Headroom; they cannot stop unrelated tools from consuming the subscription.
Examples
Runnable against synthetic data, no logins needed. Build once, then point the CLI at a seeded home:
npm run build
# sets HEADROOM_HOME to a throwaway demo home
eval "$(node scripts/demo-home.mjs)"
# walks a fallback list, dispatches on the first class with room
bash examples/orchestrator-loop.sh
# refuses a job the budget cannot cover (exit 1)
bash examples/ci-gate.sh
# the MCP call a client sends, over stdio
bash examples/mcp-quota-can.sh
The scripts refuse to run unless HEADROOM_HOME points at that demo home, so they cannot touch a real
~/.headroom, and they call the repo build (dist/cli.js), not a global headroom. They print which
binary they use.
See examples/ for the scripts and the starter accounts.toml, policy.toml and
routing.toml.
docs/quickstart.md: install to first truthful line, macOS, Linux and Windows
docs/concepts.md: principal, meter, window, observation, pace states, leases, events
docs/mcp-and-agents.md: the MCP tools, example calls, and how an orchestrator should use them
docs/json-contract.md: the versioned field-by-field shape of every --json output and MCP tool result, and its compatibility promise
docs/vendors.md: what Headroom reads per vendor, and its known live limitations
How it compares and what it reads
Headroom is not a cost tracker: ccusage estimates spend from local logs, while headroomd reads the limit the vendor enforces. They work side by side.
Headroom is unofficial. Claude is read through Claude Code itself by default; other readers use undocumented vendor endpoints with your own login. See Vendor endpoints and your accounts.
Vendor endpoints and your accounts
Several adapters read usage endpoints that the vendors do not document as public APIs. Headroom
calls them with your own credentials, taken from the vendor CLIs you installed and signed in to on
the same machine, and only to read usage: it sends no prompts, changes no account settings, and
never writes to another tool's credential store. Use it only with accounts you own. Vendor terms
may restrict this kind of access, and a vendor can change or block an endpoint at any time; use it
at your own risk. Headroom does not rotate credentials to get past a block or a limit. Use only accounts you own; Headroom does not help get around a vendor's limits.
Every request identifies itself as headroomd/<version>. The default (claude_probe = false) needs no token and no undocumented endpoint: Headroom reads the statusline snapshot, or runs Claude Code's own /usage, and never reads Claude's Keychain item or calls Anthropic. Setting claude_probe = true opts into a last-resort call, made only when no other reading is available: Headroom reads Claude Code's OAuth token and calls an undocumented Anthropic endpoint, and Anthropic's terms reserve that login for ordinary use of Claude Code.
Source
What Headroom calls
Credential
Documented by the vendor
Claude, statusline snapshot (default, preferred)
No network call: reads the JSON Claude Code passes to its statusLine command
None
Not applicable (local)
Claude, /usage fallback (default)
Runs your own claude -p "/usage" at most every 10 minutes per profile, with or without a fresh statusline snapshot; no model turn, no cost
None handled by Headroom: Claude Code uses its own login
Yes, usage_report is in the Agent SDK reference (marked experimental)
Claude, usage probe (opt-in: claude_probe = true in policy.toml)
GET api.anthropic.com/api/oauth/usage
Claude Code's OAuth token, from the macOS Keychain or .credentials.json
No. Sends User-Agent: headroomd/<version>
Codex
GET chatgpt.com/backend-api/wham/usage and .../wham/rate-limit-reset-credits; also the Codex CLI's local session logs
ChatGPT token in ~/.codex/auth.json
No. Sends User-Agent: headroomd/<version>
Antigravity quota (experimental)
agy's local language server on 127.0.0.1
agy's local CSRF token from its process command line, where present; not agy's OAuth or session credential
No (private local endpoint)
Grok (experimental)
GET cli-chat-proxy.grok.com/v1/billing?format=credits and /v1/settings
Bearer token from ~/.grok/auth.json (written by grok login)
No. Sends User-Agent: headroomd/<version>
Kimi, CLI credential
GET api.kimi.com/coding/v1/usages
Access token from ~/.kimi-code/credentials/kimi-code.json
No. Sends User-Agent: headroomd/<version>
Kimi, manual token
The www.kimi.com/apiv2 web gateway
A kimi-auth web session token you save yourself to a 0600 file (default ~/.kimi/auth.token)
No
Kimi, optional balance
GET api.moonshot.ai/v1/users/me/balance
A Moonshot API key you save to a 0600 moonshot.key file
Headroom never writes a vendor credential or notification token to disk, and redacts secrets from
its output. With claude_probe = true on macOS, a bundled helper, headroom-claude-probe, reads Claude Code's Keychain token
by running /usr/bin/security, which the Keychain item's own access list admits, keeps it in the
helper's memory and makes the usage request itself, so the token never reaches Node or Headroom's
output. With Claude Code 2.1.263 on macOS 26.5 this needed no Keychain dialog. The helper ships
inside the npm package as a universal binary, verified against a recorded SHA-256 before every use.
Tokens are otherwise read at call time from the vendor's own credential file and dropped after the
request. The daemon listens on a 0600 local socket on macOS and Linux. On Windows it uses a named
pipe where both sides prove they hold a per-daemon session token, kept in a 0600 file under
HEADROOM_HOME. There is no telemetry. Apart from
the vendors you configure and the notification channels you enable, the only request Headroom
makes unprompted is the daily npm version check above, a plain GET with no account data
(update_check = false turns it off); headroom update and headroom engine install contact npm
and GitHub only when you run them. The engine is pinned and checksum verified, and every query
lands in an audit log. Details in SECURITY.md.
Status
Releases are published to npm as headroomd; CHANGELOG.md lists what changed in
each one. Vendor endpoints are private and
change without notice: Headroom pins them, records fixtures, backs off on 401, 403 and 429, and
prints UNKNOWN instead of a stale number. What is and is not verified is in
Platform support and known limitations. Antigravity requires macOS and a daemon-kept agy; see
vendor setup.