Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/terrene-foundation/kailash-coc-claude-pynpx agentmods add commands/terrene-foundation/kailash-coc-claude-py/cost-auditWrote 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/terrene-foundation/kailash-coc-claude-py/cost-audit)<a href="https://agentmods.dev/commands/terrene-foundation/kailash-coc-claude-py/cost-audit"><img src="https://agentmods.dev/badge/commands/terrene-foundation/kailash-coc-claude-py/cost-audit/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/terrene-foundation/kailash-coc-claude-py/cost-audit"><img src="https://agentmods.dev/badge/commands/terrene-foundation/kailash-coc-claude-py/cost-audit.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00030 | $0.00571 |
| Opus 5 | $0.00015 | $0.00285 |
| Sonnet 5 | $0.00006 | $0.00114 |
| Haiku 4.5 | $0.00003 | $0.00057 |
Grade A, and why
cost-audit 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 7d 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 — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/cost-audit reports the API-list-price value of your Claude Code token usage, grouped
by project, read from the transcripts under <home>/.claude/projects/. It is
read-only and needs no network or credentials.
What the number means. Claude Code persists exact token counts per message but no dollar figure; this re-values those tokens at Anthropic API list prices. Under a flat subscription the dollars are NOTIONAL (attribution, not a bill); under API-key billing they approximate real metered spend. Either way the token volume is exact.
Accuracy. Correct per-model rates (Opus 4.8 = $5/$25, deprecated 4.1/4 = $15/$75,
Sonnet 5, Haiku 4.5, Fable 5, fast mode), the 1h/5m cache-write tiers, subagent
transcripts, dedup of resumed/forked sessions, and iterations[] de-duplication are
all handled. Worktrees and subdirectories fold into their git repo root by default.
Steps
-
Run the report (read-only). Pass through any
$ARGUMENTS:node .claude/bin/cc-cost.mjs $ARGUMENTSFlags:
--since YYYY-MM-DD·--sessions·--by-model·--no-fold(keep worktrees separate) ·--top N·--json·--rates FILE·--help. -
Present the table (or the requested cut) to the user in plain language. If they named a repo, a date range, or asked for JSON, pass the matching flags. If the
UNPRICED modelsfooter lists non-Claude models (deepseek / glm / minimax), note that those are excluded until rates are supplied. Do NOT modify any files.
Notes
- Cross-platform. Resolves the home directory portably and shells out to
gitonly to fold worktrees. Ifgitis not on PATH (or a directory is not a repo), it falls back to grouping by working directory — no crash, just less folding. - Authoritative cost. The exact figure Claude Code's own statusline shows lives only in the running process's memory and is not persisted anywhere; this report is the best on-disk reconstruction, not that live counter.
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.
- 7d ago First seen · 45 lines · 30 tokens per session scan A 5696c0ecd03d
cost-audit is a command published in the GitHub repository terrene-foundation/kailash-coc-claude-py (12 stars, last pushed 23d ago), licensed Apache-2.0. It adds 30 tokens to every session and 571 once invoked, about $0.0002 per session on Opus 5. 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 2026-09-03.
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.