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/beginnersinai/the-44-percent-ruleWrote 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/beginnersinai/the-44-percent-rule/gap-finder)<a href="https://agentmods.dev/agents/beginnersinai/the-44-percent-rule/gap-finder"><img src="https://agentmods.dev/badge/agents/beginnersinai/the-44-percent-rule/gap-finder/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/beginnersinai/the-44-percent-rule/gap-finder"><img src="https://agentmods.dev/badge/agents/beginnersinai/the-44-percent-rule/gap-finder.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 | $0.00088 | $0.01059 |
| Opus 5 | $0.00044 | $0.00530 |
| Sonnet 5 | $0.00018 | $0.00212 |
| Haiku 4.5 | $0.00009 | $0.00106 |
Grade A, and why
gap-finder 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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
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 · 112 lines · 88 tokens per session scan A 755b396feaa9
gap-finder is an agent published in the GitHub repository beginnersinai/the-44-percent-rule (2 stars, last pushed 4mo ago), with no licence file. It adds 88 tokens to every session and 1,059 once invoked, about $0.0004 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 2026-08-31.
Other agents, from other repositories
100x-engineer
Autonomous full-stack engineer that takes a requirement from idea to production-ready code. Researches best approaches, prototypes unknowns, builds a comprehensive plan broken into waves of parallel tasks, executes via sub-agents, tests everything, audits for security, and delivers a final handoff report with any…
orchestrator
Entry point for all Lumen PM workflows (W1–W6). Sequences sub-agents, enforces tier gates and oversight approvals, tracks evidence quality, and generates reports. Use to run PMF discovery, churn recovery, feature validation, launch planning, or strategy workflows.
decide_well
Structured decision-making for high-stakes, often irreversible product choices. Use when facing a decision that requires trade-off analysis, pre-mortem, or consensus across conflicting agent outputs. Oversight level 2 — pauses for PM approval.
ecosystem_os
Design developer platform, partner ecosystem, and API product strategy. Use for enterprise-tier developer experience design, TTFC optimisation, and partner pipeline planning. Oversight level 2.
setup_guide
Run automatically at the start of every Lumen session to validate MCP connections and seed the context object. Produces setupstate and businessmodeltype. Do not invoke directly — the Orchestrator calls this first.
data_layer
AI ethics, data governance, and schema validation checkpoint. Use for W4 feature validation ethics clearance, compliance audits, and data lineage verification. Oversight level 3 — requires human approval on BLOCKED decisions.