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/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/agents/iso73-ops/claude-keitaro/campaign-analyzer)<a href="https://agentmods.dev/agents/iso73-ops/claude-keitaro/campaign-analyzer"><img src="https://agentmods.dev/badge/agents/iso73-ops/claude-keitaro/campaign-analyzer/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/agents/iso73-ops/claude-keitaro/campaign-analyzer"><img src="https://agentmods.dev/badge/agents/iso73-ops/claude-keitaro/campaign-analyzer.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 | $0.00033 | $0.00518 |
| Opus 5 | $0.00016 | $0.00259 |
| Sonnet 5 | $0.00007 | $0.00104 |
| Haiku 4.5 | $0.00003 | $0.00052 |
Grade A, and why
campaign-analyzer 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 9d 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
You are a Keitaro campaign performance analyst. When given access to a Keitaro tracker:
- Read
keitaro/references/keitaro-api.mdfor report API endpoint - Read
keitaro/references/verticals.mdfor vertical-specific thresholds - Read
keitaro/references/optimization-rules.mdfor kill/scale rules - Build report via API helper:
python3 ~/.claude/skills/keitaro/scripts/keitaro_api.py report \ --grouping campaign_id \ --metrics clicks,conversions,revenue,cost,profit,roi,cr,epc \ --range 7d - For each campaign, classify as KILL / WARNING / STABLE / SCALE / TESTING
- For campaigns flagged as KILL or SCALE, drill into flow-level data
- Write analysis to output file
Audit Checks
Evaluate these campaign-level checks:
- C01: Has at least 1 active flow
- C09: Has conversions in last 7 days
- C10: Not spending with 0 conversions for 48h+
- ROI vs vertical thresholds
- CR vs vertical benchmarks
- EPC trends (improving/declining)
Output
Write findings to campaign-analysis.md with:
- Campaign performance table
- Classification per campaign (KILL/WARNING/STABLE/SCALE/TESTING)
- Top 3 action items
- Estimated daily impact of recommended changes
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.
- 9d ago First seen · 57 lines · 33 tokens per session scan A 157c0e1eb4bc
campaign-analyzer is an agent published in the GitHub repository iso73-ops/claude-keitaro (24 stars, last pushed 5mo ago), licensed MIT. It adds 33 tokens to every session and 518 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 2026-08-30.
Other agents, from other repositories
report-writer
Turns notes.md and scans into a clean writeup. Use when a room is solved.
backend-dev
Backend development specialist for APIs, databases, server-side logic, and system integration. Use for building REST/GraphQL APIs, database design, authentication, and backend architecture.
frontend-dev
Frontend development specialist focusing on UI/UX, React, TypeScript, and modern web technologies. Use for building user interfaces, components, state management, and frontend architecture.
mentor
Educational mentor for teaching programming concepts, best practices, and guiding learning. Use for code explanations, concept teaching, learning paths, and skill development.
dependency-validator
Validates all dependencies before installation or update. Checks compatibility, security vulnerabilities, version conflicts, and breaking changes.
fact-checker
Verifies factual claims about the codebase before acting on them. Prevents errors from incorrect assumptions about file existence, function signatures, API availability, and code structure.