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/sessiongit 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 | $0.01244 |
| Opus 5 | $0.00000 | $0.00622 |
| Sonnet 5 | $0.00000 | $0.00249 |
| Haiku 4.5 | $0.00000 | $0.00124 |
Grade A, and why
session 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.
How it starts
The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
session
Claude usage grouped by sessionId. Resumed sessions (same sessionId
across multiple JSONL files via claude --resume) collapse into a single
row. 11-column layout that parallels codex-session.
Cost coverage: Claude dollar and token totals are transcript-derived lower bounds, not exact
/usagebilling totals.
Canonical form:
cctally claude session(this flat form remains as an alias).
Synopsis
cctally session
[-s YYYYMMDD] [-u YYYYMMDD]
[-b] [-o {asc,desc}]
[-m {auto,calculate,display}]
[--json]
Options
| Flag | Description |
|---|---|
-s, --since YYYYMMDD |
Filter from date (inclusive). |
-u, --until YYYYMMDD |
Filter until date (inclusive). |
-b, --breakdown |
Show per-model cost breakdown sub-rows. |
-o, --order {asc,desc} |
Sort direction by last activity (default asc — earliest first). |
-m, --mode {auto,calculate,display} |
Cost source (drop-in for ccusage session --mode). auto (default) uses the recorded costUSD from JSONL when present, else computes from embedded pricing. calculate always computes from embedded pricing, ignoring any recorded costUSD. display shows the recorded costUSD only, rendering $0.00 when a session has none (ccusage-faithful). Most modern Claude Code JSONL omits costUSD, so under display near-everything reports $0. |
--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). |
--json |
Output JSON. |
Behavior note (
auto, sessions with legacycostUSD). Before the--modework,sessionwas the one report that always recomputed cost from embedded pricing and ignored any recordedcostUSD— even thoughdaily,monthly,weekly, and the dashboard already preferred the recorded value. The defaultautomode now alignssession(and the TUI session views, which have no--modeflag) with those reports: for sessions whose JSONL carriescostUSD, default totals reflect the recorded cost rather than a recomputed one. Only the ~3.9% of historical files that still carrycostUSDare affected; everything else is unchanged. Pass--mode calculateto force the old always-recompute behavior.
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.
- 2d ago First seen · 105 lines · 0 tokens per session scan A ace4374fa77d
session 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 1,244 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.