forecast

A command that estimates how much of the current week’s Claude usage will be reached by the reset time. Claude is an AI assistant, and the reset boundary is when its usage allowance starts over.

In plain words
What is it for?
Use it for a terminal report, machine-readable JSON, or a short status-line message showing projected usage and daily budget guidance.
Why use it?
It warns when your current pace may reach the limit, helping you adjust before usage is capped.

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/omrikais/cctally/forecast
Clone the repo
git clone --depth 1 https://github.com/omrikais/cctally
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,434 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 $0.00000 $0.02434
Opus 5 $0.00000 $0.01217
Sonnet 5 $0.00000 $0.00487
Haiku 4.5 $0.00000 $0.00243

Measured 2d ago against content hash 5c9cb99fa2ac, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

forecast 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 2d 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.

docs/commands/forecast.md · 147 lines

How it starts

The opening of the file, as written. The whole thing — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.

cctally forecast

Project current-week usage to the reset boundary. Produces three forms of output from the same computation:

  • Default: a box-framed terminal report with a progress bar, forecast range, and daily $ / % budgets at configurable ceilings.
  • --json: the same data as a machine-readable payload.
  • --status-line: a compact one-line segment sized for embedding in ~/.claude/statusline-command.sh.

Cost coverage: Claude dollar and token totals are transcript-derived lower bounds, not exact /usage billing totals.

When it helps

Mid-week, glance at the status line; if the projection range creeps toward 90%+, you're pacing above your sustainable rate and can look at the full report (cctally forecast) to see how much $ or % of quota per day keeps you under 100%.

Output states

  • Safe (high < 90): cyan projection range.

  • Approaching (90 <= high < 100): yellow projection with "approaching 100%" note.

  • Projected cap (high >= 100): red projection + ⚠ may cap; status line appends the to-90% $/day budget; terminal report shows projected cap_at timestamp in the footer.

  • Already capped (p_now >= 100): red ⚠ CAPPED banner; budget section omitted.

  • Low confidence: shown when any of four triggers fires. Terminal shows the forecast range dimmed with a LOW CONF label followed by the reasons in plain words; status line reduces to tracking…. The four triggers, with the reason code each one emits in --json and the wording the terminal renders for it:

    Trigger --json code Terminal wording
    Fewer than 24 hours have elapsed since the week started elapsed_hours<24 less than 24 hours into the week
    The account has used under 2% of its weekly quota so far percent<2 under 2% of quota used so far
    Fewer than 3 usage snapshots have been recorded this week snapshots<3 fewer than 3 usage snapshots
    No usage snapshot is at least 24 hours old, so no rate can be measured over a full day no_sample_ge_24h no snapshot at least 24 hours old

Read the full file on GitHub · 147 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.

  1. 2d ago First seen · 147 lines · 0 tokens per session scan A 5c9cb99fa2ac

Subscribe to this mod's changes

forecast is a command published in the GitHub repository omrikais/cctally (5 stars, last pushed 4d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 2,434 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 2026-08-31.