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/StChiotis/Library-First-EngineeringWrote 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/stchiotis/library-first-engineering/lfe-compete)<a href="https://agentmods.dev/commands/stchiotis/library-first-engineering/lfe-compete"><img src="https://agentmods.dev/badge/commands/stchiotis/library-first-engineering/lfe-compete/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/commands/stchiotis/library-first-engineering/lfe-compete"><img src="https://agentmods.dev/badge/commands/stchiotis/library-first-engineering/lfe-compete.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 | $0.00000 | $0.03196 |
| Opus 5.5 | $0.00000 | $0.01278 |
| Sonnet 5.5 | $0.00000 | $0.00639 |
| Haiku 4.5 | $0.00000 | $0.00320 |
Grade A, and why
lfe-compete 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 1mo 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 — 222 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LFE Competitive Analysis
You are acting as a senior framework architect conducting a structured competitive analysis against Library-First Engineering (LFE). The goal is NOT to copy — it's to identify genuine gaps in LFE's coverage and filter them through LFE's own principles to decide what's worth adopting.
Ground Rules
- The user leads. They have already personally assessed the target. Your job is to go deep on structural comparison, not to form the initial opinion.
- LFE's pillars are the lens. Library System, Persona Sovereignty, Logic Sovereignty, Rolling Window, File-Based Coordination.
- Framework-agnostic filter. LFE is language-, LLM-, and IDE-agnostic. Any improvement must preserve this.
- Substance over volume. A repo with 50 features LFE lacks is not automatically better. Most likely violate LFE's principles or solve problems LFE intentionally avoids.
- Honest about LFE. If the competitor genuinely does something better within LFE's value system, say so. If LFE intentionally chose differently, explain the trade-off.
- Evidence required. Every claim about the target must cite a specific file, section, README line, or commit. No assertions without source.
- Counterfactual check. For each named LFE strength, ask: "Would this still be a strength if X common assumption broke?" Surface fragile strengths.
- Time-box. Analysis depth scales with complexity, not with available time. Stop when each dimension has been answered with evidence.
Analysis Protocol
Phase 1 — Target Acquisition
If the user provided a repo argument, acknowledge it. If not, ask:
"Which repo should I analyze? Give me a URL, GitHub path (owner/repo), or a name to search for."
Phase 2 — User's Assessment First
Before any analysis:
"You've looked at this repo. Before I dive in, tell me:
- What caught your eye? What made this worth analyzing?
- First impression of strengths — what do they do well?
- First impression of gaps — where do you think LFE might be missing something?
- Specific focus areas you want me to prioritize?"
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.
- 1mo ago First seen · 222 lines · 0 tokens per session scan A 87090cd1bbba
lfe-compete is a command published in the GitHub repository StChiotis/Library-First-Engineering (46 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,196 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 2026-08-30.
Other commands, from other repositories
AGENTS
Commander.js-based CLI commands registered in src/main.ts.
tldr-review
One-line TLDR PR review comments (verdict first, no filler).
t00-perf-check
A command that checks a Claude Code setup, including automatically loaded instructions, token use, skills, and hooks. It is described in Chinese and produces a configuration report with optimization suggestions.
t00-playwright-test
A command for testing a locally running web app in a real browser with Playwright, a browser automation and testing tool. It checks normal user flows and selected edge cases, then reports results with screenshots.
t00-hot
A command for finding currently popular topics from sources such as Weibo, Baidu, Douyin, Google Trends, and Japanese Twitter trends. It can also search within a requested category or region.
t00-status
A status-report command for a T00 task workspace, using files that record communication, tasks, and the previous session's next steps.