Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
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.
[](https://agentmods.dev/commands/omrikais/cctally/five-hour-breakdown)<a href="https://agentmods.dev/commands/omrikais/cctally/five-hour-breakdown"><img src="https://agentmods.dev/badge/commands/omrikais/cctally/five-hour-breakdown.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00000 | $0.01918 |
| Opus 5 | $0.00000 | $0.00959 |
| Sonnet 5 | $0.00000 | $0.00384 |
| Haiku 4.5 | $0.00000 | $0.00192 |
Grade A, and why
five-hour-breakdown 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 6d 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.
How it starts
The opening of the file, as written. The whole thing — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.
five-hour-breakdown
Per-percent cumulative + marginal cost milestones inside a single
API-anchored 5-hour block. Mirror of percent-breakdown for the 5h axis.
Cost coverage: Stored Claude milestone costs are transcript-derived lower bounds, not exact
/usagebilling totals.
Which 5h command?
blocksis the ccusage-compatible per-window view (includes~-prefixed heuristic rows when no recorded reset covers a window);five-hour-blocksis the API-anchored analytics view with model/project rollups and 7d drift;five-hour-breakdown(this page) drills into per-percent milestones inside one block.
Synopsis
cctally five-hour-breakdown
[--block-start ISO8601 | --ago N]
[--json] [--no-color] [--tz TZ]
Purpose
When record-usage sees a 5h-window snapshot crossing an integer percent
threshold, it writes a row to five_hour_milestones. This command renders
those rows for one block so you can see exactly when each percent was
reached and what it cost incrementally — the same lens as
percent-breakdown, but scoped to a 5h window instead of a week.
Block selector
| Flag | Behavior |
|---|---|
| (none — default) | Current/most-recent API-anchored block (active or last-closed). |
--block-start <iso> |
Explicit. Accepts ISO 8601 with offset (2026-04-30T19:30:00Z, 2026-04-30T22:30:00+03:00) or naive (2026-04-30T19:30). Naive selectors are interpreted as UTC. Date-only inputs (2026-04-30) are rejected with exit 2. |
--ago N |
Relative; 0 = current, 1 = previous, …. Mutually exclusive with --block-start. |
--tz affects display only; it does NOT shift selector parsing.
The selector resolves through _canonical_5h_window_key, so any
timestamp within the same 10-minute floor as the actual block matches
correctly.
Options
| Flag | Description |
|---|---|
--block-start ISO8601 |
Explicit selector (see above). |
--ago N |
Relative selector (see above). |
--json |
Emit camelCase JSON (schemaVersion: 1). |
--no-color |
Disable ANSI color (currently a no-op — table is plain text). |
--tz TZ |
Display timezone for this call (local, utc, or IANA, e.g. America/New_York). Overrides config display.tz. See Display timezone for the full contract (parsing scope, JSON UTC invariant). Note: --block-start selector parsing is not display-tz-shifted (see callout in "Block selector" above). |
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.
- 6d ago First seen · 180 lines · 0 tokens per session scan A bfd04995c809
five-hour-breakdown is a command published in the GitHub repository omrikais/cctally (5 stars, last pushed 2d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,918 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.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
constitution
Create or update the project constitution from interactive or provided principle inputs.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.