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/vukkt/token-warden/warden-benchgit 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-bench)<a href="https://agentmods.dev/commands/vukkt/token-warden/warden-bench"><img src="https://agentmods.dev/badge/commands/vukkt/token-warden/warden-bench.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 | $0.00028 | $0.00372 |
| Opus 5 | $0.00014 | $0.00186 |
| Sonnet 5 | $0.00006 | $0.00074 |
| Haiku 4.5 | $0.00003 | $0.00037 |
Grade A, and why
warden-bench 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.
What it actually says
Run the golden-suite benchmark. The agent (or all) and any extra flags are:
$ARGUMENTS
If no agent was given, use all. Build and run this command (it spawns
headless Claude sessions per golden task, so it can take several minutes per
agent — run it in the background and report progress):
cd "${CLAUDE_SKILL_DIR}/.." && npx tsx src/bench.ts --agent <agent-or-all> <extra flags as given>
When it finishes, report:
- Per task: the mean completed tokens, the comparison against the frozen
run1baseline (the printed percentage) and thebestfigure. - The meta-cost line at the end — and if the overhead warning is present, surface it prominently: it means benchmarking spent more than 10% of the week's collected real-work tokens, and the user should bench less often.
- Any per-task
runs differ by >25%variance warnings. - If the run prints
ENVIRONMENT FAILUREand aborts, report that the benchmark died environmentally (4 consecutive zero-token failed runs — quota exhaustion / API outage) and should be re-run on a fresh quota window; results recorded before the abort are valid.
Never edit run1 values or the database by hand; baselines are frozen by
design.
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 · 34 lines · 28 tokens per session scan A 300239859ee2
warden-bench is a command published in the GitHub repository vukkt/token-warden (13 stars, last pushed 4d ago), licensed MIT. It adds 28 tokens to every session and 372 once invoked, about $0.0001 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
memory-report
Calibration + inventory check of your causal memory (prediction ledger accuracy, what you know).
recall
Recall past experience relevant to a task or decision before acting on it.
remember-compact
Save current conversation, then remind me to compact.
remember
Save the current conversation into active memory.
tokenless-stats
Show Tokenless compression statistics.
sync
Manually trigger plan-sync to update downstream task specs after implementation drift.