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 skills add iso73-ops/claude-keitaro --skill keitaro-auditgit clone --depth 1 https://github.com/iso73-ops/claude-keitaroWrote 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/skills/iso73-ops/claude-keitaro/keitaro-audit)<a href="https://agentmods.dev/skills/iso73-ops/claude-keitaro/keitaro-audit"><img src="https://agentmods.dev/badge/skills/iso73-ops/claude-keitaro/keitaro-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/skills/iso73-ops/claude-keitaro/keitaro-audit"><img src="https://agentmods.dev/badge/skills/iso73-ops/claude-keitaro/keitaro-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 | $0.00057 | $0.01281 |
| Opus 5 | $0.00028 | $0.00641 |
| Sonnet 5 | $0.00011 | $0.00256 |
| Haiku 4.5 | $0.00006 | $0.00128 |
Grade A, and why
keitaro-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 11d 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 — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Keitaro Campaign Audit
Process
- Read
keitaro/references/keitaro-api.mdfor API endpoints - Read
keitaro/references/flow-patterns.mdfor expected patterns - Read
keitaro/references/optimization-rules.mdfor thresholds - Pull all campaign and flow data
- Run audit checks
- Generate health report with findings
Audit Checks (35 total)
Campaign Health (10 checks)
| ID | Check | Severity |
|---|---|---|
| C01 | Campaign has at least 1 active flow | Critical |
| C02 | Campaign has a default flow (white page) | High |
| C03 | Campaign is linked to a traffic source | Medium |
| C04 | Campaign has a domain assigned | High |
| C05 | Campaign alias is set and valid | Medium |
| C06 | Campaign cost model is configured | Medium |
| C07 | Campaign has no empty/orphan flows | Low |
| C08 | Campaign name follows naming convention | Low |
| C09 | Campaign has conversions in last 7 days | Warning |
| C10 | Campaign is not spending with 0 conversions for 48h+ | Critical |
Flow Health (10 checks)
| ID | Check | Severity |
|---|---|---|
| F01 | Flow has at least 1 landing or offer assigned | Critical |
| F02 | Flow filters are not contradictory | High |
| F03 | Flow GEO filter matches campaign intent | Medium |
| F04 | Flow weight is > 0 for active flows | Medium |
| F05 | Flow schema matches landing/offer setup | High |
| F06 | Total flow weights don't exceed 100 logical distribution | Low |
| F07 | No duplicate flows (same filters + same landings) | Low |
| F08 | Default flow exists and has a safe landing | High |
| F09 | Flow is receiving traffic (clicks > 0 in 48h) | Warning |
| F10 | Flow ROI is not critically negative (< -50%) | Critical |
Postback & Tracking (8 checks)
| ID | Check | Severity |
|---|---|---|
| T01 | Affiliate network has postback URL configured | Critical |
| T02 | Postback URL contains required macros ({subid}, etc.) | Critical |
| T03 | Conversions received in last 7 days | High |
| T04 | Conversion count matches approximate offer network stats | Medium |
| T05 | Traffic source postback configured (for auto-cost) | Medium |
| T06 | Click-to-conversion time is reasonable (not instant) | Medium |
| T07 | No duplicate conversions detected | High |
| T08 | S2S postback preferred over pixel (reliability) | Low |
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.
- 11d ago First seen · 142 lines · 57 tokens per session scan A 910ebb344b1c
keitaro-audit is a skill published in the GitHub repository iso73-ops/claude-keitaro (24 stars, last pushed 5mo ago), licensed MIT. It adds 57 tokens to every session and 1,281 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 skills, from other repositories
financial-planner
Your Personal Finance Manager for Canadians — an AI financial planning partner that conducts thorough financial interviews, builds complete plans, generates interactive dashboards, and provides ongoing coaching. Use this skill whenever someone asks about budgeting, saving, investing, debt strategy, retirement…
powerpoint-mcp
PowerPoint MCP Server skill for Windows presentation automation via a live PowerPoint desktop instance (COM/PIA). Use when an assistant needs rich MCP tools to create, open, build, format, and export PowerPoint (.pptx/.pptm) presentations — slides, shapes, text boxes, tables, native charts, images, audio, video…
vibe-ship
Generates a complete, production-ready deployment setup for any app in one pass -- Dockerfile, docker-compose.yml, .dockerignore, CI/CD (GitHub Actions), scalability config (health checks, resource limits, K8s on request), and security hardening (non-root user, secrets, dependency scanning). Auto-detects the stack…
swarm
Run a multi-agent audit of a codebase by spawning specialized parallel subagents (security, performance, tests, architecture, dead-code), then synthesize their findings into a single prioritized action plan. Use this whenever the user runs /swarm, asks to "audit the repo," "review this codebase," "find issues across…
log-correlation
Correlates and troubleshoots logs across OS (Linux/macOS), AWS (CloudWatch, CloudTrail, ALB, Lambda), application (JSON, logfmt), and web servers (Nginx, Apache).
eng-unity-mobile-optimization
Mobile-specific Unity optimization patterns for memory, battery, thermal, and performance.