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.
npx agentmods add commands/omrikais/cctally/diffgit clone --depth 1 https://github.com/omrikais/cctallyWhat 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 | $0.00000 | $0.03286 |
| Opus 5 | $0.00000 | $0.01643 |
| Sonnet 5 | $0.00000 | $0.00657 |
| Haiku 4.5 | $0.00000 | $0.00329 |
Grade A, and why
diff 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.
How it starts
The opening of the file, as written. The whole thing — 281 lines — stays where its author put it; the contents beside it link to each section on GitHub.
diff
Compare Claude usage between two windows in a single bordered-table render. Answers "what changed between this week and last week — and which models, projects, and cache patterns drove the change?"
Claude cost coverage: Claude dollar and token totals are transcript-derived lower bounds, not exact
/usagebilling totals. Codex accounting is unaffected.
Quick examples
# This subscription week vs last
cctally diff --a this-week --b last-week
# This calendar month vs last
cctally diff --a this-month --b last-month
# Rolling 7d vs the previous 7d (lengths match by construction)
cctally diff --a last-7d --b prev-7d
# Compare windows of different length (per-day normalization)
cctally diff --a last-7d --b prev-14d --allow-mismatch
# Drill into a single section (skip the others)
cctally diff --a this-week --b last-week --only cache
# Show every row including those filtered as noise
cctally diff --a this-week --b last-week --all
# Machine-readable output
cctally diff --a this-week --b last-week --json | jq
Window grammar
The --a and --b tokens share the same grammar:
| Form | Meaning |
|---|---|
this-week |
Current subscription week — start at the most-recent reset anchor, end at now. |
last-week |
Previous full subscription week. |
Nw-ago |
Subscription week N resets back from the current (1w-ago ≡ last-week). |
this-month |
Current calendar month in the user's local TZ. |
last-month |
Previous full calendar month. |
Nm-ago |
Calendar month N months back. |
last-Nd |
Trailing N days ending at now ([now − Nd, now)). |
prev-Nd |
The N-day window immediately before last-Nd ([now − 2Nd, now − Nd)). |
YYYY-MM-DD..YYYY-MM-DD |
Explicit inclusive date range, interpreted in local TZ. |
Subscription-week tokens fall back to the canonical 7-day-multiple
offset when no snapshot exists at the target week (same logic weekly
uses). If even the earliest anchor is missing, the command exits with
diff: no subscription-week anchor available … and exit code 1.
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.
- yesterday First seen · 281 lines · 0 tokens per session scan A 893f0ebc0114
diff is a command published in the GitHub repository omrikais/cctally (5 stars, last pushed 3d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 3,286 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.
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.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.