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/blpsoares/agentistics/nay-auditgit clone --depth 1 https://github.com/blpsoares/agentisticsWrote 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/blpsoares/agentistics/nay-audit)<a href="https://agentmods.dev/commands/blpsoares/agentistics/nay-audit"><img src="https://agentmods.dev/badge/commands/blpsoares/agentistics/nay-audit.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 | $0.00000 | $0.00278 |
| Opus 5 | $0.00000 | $0.00139 |
| Sonnet 5 | $0.00000 | $0.00056 |
| Haiku 4.5 | $0.00000 | $0.00028 |
Grade A, and why
nay-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 3d 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
Use the Nay agent to run a full productivity and efficiency audit of my Claude Code usage.
Nay should:
- Call
agentistics_summaryfor totals. - Call
agentistics_projectsto see all projects. - Call
agentistics_sessionswith limit=100 to analyze patterns. - Call
agentistics_costsfor the model/cache breakdown.
Produce an audit report with these sections:
Productivity
- Sessions per day (average and trend)
- Average session duration
- Most active days of the week
- Current streak vs. longest streak
- Projects with most vs. least activity
Efficiency
- Cache hit rate — is it above 50%? If not, what could help
- Average tokens per session by model
- Cost per session by model — are expensive models being used for simple tasks?
- Sessions under 2 minutes (possibly wasted context) vs. long deep-work sessions
Project health
- Projects with no sessions in the last 7 days (inactive)
- Projects with the highest cost per session (worth reviewing workflows)
- Projects with best cache efficiency (good patterns to replicate)
Recommendations
Give 3–5 concrete, actionable recommendations based on the data. Flag anything that looks like waste or an opportunity to save.
Keep the full audit under 600 words. Use tables for all comparisons.
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.
- 3d ago First seen · 34 lines · 0 tokens per session scan A a888738011d4
nay-audit is a command published in the GitHub repository blpsoares/agentistics (39 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 278 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 2026-09-01.
Other commands, from other repositories
suggest-automation
반복 패턴 분석하여 자동화 기회 제안 (주기적 실행 권장).
instinct-export
Export instincts for sharing with teammates or other projects.
setup
Set up connect-apps - let Claude perform real actions in 500+ apps.
optimise-macos-indexing-backups
Audit and optionally apply safe macOS indexing and backup exclusions.
context-stats
Display context window usage and token statistics.
run
Execute prompt(s) from ./prompts/ with automatic archiving - for structured prompt-based work.