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.
git clone --depth 1 https://github.com/vukkt/token-wardenWrote 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/vukkt/token-warden/warden-cost)<a href="https://agentmods.dev/commands/vukkt/token-warden/warden-cost"><img src="https://agentmods.dev/badge/commands/vukkt/token-warden/warden-cost.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 | $0.00053 | $0.00445 |
| Opus 5 | $0.00026 | $0.00222 |
| Sonnet 5 | $0.00011 | $0.00089 |
| Haiku 4.5 | $0.00005 | $0.00044 |
Grade A, and why
warden-cost scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Run the token-warden dollar report (read-only; it prices the stored receipts):
cd "${CLAUDE_SKILL_DIR}/.." && npx tsx src/cost.ts $ARGUMENTS
Argument forms (pass through verbatim as $ARGUMENTS):
- (no args) — per-rule dollar report for every domain agent
--agent sql— one agent--json— machine-readable output--project— horizon projection (default 13 weeks ≈ 3 months): gross savings, operating (discovery) cost, NET benefit, break-even, and the cost with vs without the plugin over that span--months 6/--weeks 26— set the projection horizon (implies--project)--sessions-per-week 40— assumed session volume for the projection (implies--project; defaults toWARDEN_SESSIONS_PER_WEEK)
Prices default to the public Anthropic rate card; override any rate with the
TOKEN_WARDEN_PRICE_INPUT / _OUTPUT / _CACHE_WRITE / _CACHE_READ env vars
(in $/1M tokens) to apply your own per-token prices.
Relay the report to the user. Always preserve the honest accounting note it prints: savings are priced at the agent's blended $/token mix (most saved tokens are cheap input/cache-read, so the dollar figure is the truthful magnitude, not an inflated output-rate number), and rent is priced at the input rate. The keep/evict decision itself still runs in tokens — this is the dollar lens on it, not a second gate.
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.
- 8d ago First seen · 35 lines · 53 tokens per session scan A 9b630fdd48fb
warden-cost is a command published in the GitHub repository vukkt/token-warden (13 stars, last pushed today), licensed MIT. It adds 53 tokens to every session and 445 once invoked, about $0.0003 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 2026-08-30.
Other commands, from other repositories
recall
Recall past experience relevant to a task or decision before acting on it.
memory-report
Calibration + inventory check of your causal memory (prediction ledger accuracy, what you know).
analyze
Use when the user asks to categorize spending, group by merchant or category, rank top merchants, or show monthly trends on converted statements. Do not use for first-time PDF conversion, period reconciliation, or benchmark scoring.
convert
Use when the user attaches a bank statement PDF or asks for CSV/XLSX/QBO/Xero export of a converted statement. Do not use for spending analysis, reconciliation, or benchmark scoring — those have their own skills.
reconcile
Use when the user asks to check statement coverage, missing periods, balance continuity, or cross-account transfers. Do not use for converting a new PDF, spending categorization, or benchmark scoring.
pn-audit-performance-fe
Surgical frontend performance audit — Core Web Vitals, bundle size, image optimization, render-blocking resources, and page-type budgets. Standalone or chained by pn-frontend-audit.