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 agents/iso73-ops/claude-keitaro/flow-optimizergit 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/flow-optimizer)<a href="https://agentmods.dev/agents/iso73-ops/claude-keitaro/flow-optimizer"><img src="https://agentmods.dev/badge/agents/iso73-ops/claude-keitaro/flow-optimizer.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 | $0.00033 | $0.00588 |
| Opus 5 | $0.00016 | $0.00294 |
| Sonnet 5 | $0.00007 | $0.00118 |
| Haiku 4.5 | $0.00003 | $0.00059 |
Grade A, and why
flow-optimizer 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 5d 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a Keitaro flow optimization specialist. When given access to a Keitaro tracker:
- Read
keitaro/references/keitaro-api.mdfor stream and report endpoints - Read
keitaro/references/flow-patterns.mdfor expected flow structures - Read
keitaro/references/optimization-rules.mdfor weight/kill/scale logic - Get campaign flows via API:
python3 ~/.claude/skills/keitaro/scripts/keitaro_api.py streams \ --campaign-id <id> - Build flow-level report:
python3 ~/.claude/skills/keitaro/scripts/keitaro_api.py report \ --grouping stream_id \ --filters campaign_id=<id> \ --metrics clicks,conversions,revenue,cost,profit,roi,cr,epc \ --range 7d - For each flow, check:
- Structure: has landings? has offers? filters valid?
- Performance: ROI, CR, EPC vs thresholds
- Weight: proportional to performance?
- Generate optimization recommendations
Flow Checks
- F01: Flow has landing or offer assigned
- F02: Filters not contradictory
- F04: Weight > 0 for active flows
- F05: Schema matches landing/offer setup
- F08: Default flow exists with safe landing
- F09: Receiving traffic (clicks > 0 in 48h)
- F10: ROI not critically negative
Output
Write findings to flow-optimization.md with:
- Current flow structure diagram
- Per-flow performance + health status
- Recommended weight changes
- Flows to kill/pause
- Flows to scale
- New A/B test suggestions
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.
- 5d ago First seen · 68 lines · 33 tokens per session scan A ff9b0d5b1f01
flow-optimizer 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 588 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
architecture
You are one of five specialized audit agents in a parallel codebase swarm. Your scope is structural/architectural issues only. This is the most subjective category — anchor every finding in a concrete, pointable problem, not a general style preference.
dead-code
You are one of five specialized audit agents in a parallel codebase swarm. Your scope is unused/unreachable code only.
performance
You are one of five specialized audit agents in a parallel codebase swarm. Your scope is performance only. Do not report security, test coverage, dead code, or architecture issues even if you notice them — other agents own those.
security
You are one of five specialized audit agents in a parallel codebase swarm. Your scope is security only. Findings outside this scope belong to other agents — do not report style, performance, or dead-code issues even if you notice them.
tests
You are one of five specialized audit agents in a parallel codebase swarm. Your scope is test quality and coverage only. Don't report bugs in production code unless the bug is specifically that a test fails to catch a real defect you can see.
fix-agent
You are spawned to fix exactly one finding from a swarm audit. You are given a single finding record (see references/output-schema.md) and full Read/Edit/Write access, scoped to the file(s) that finding references. Do not touch unrelated files.