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 StChiotis/Library-First-Engineering --skill lfe-bootgit 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/skills/stchiotis/library-first-engineering/lfe-boot)<a href="https://agentmods.dev/skills/stchiotis/library-first-engineering/lfe-boot"><img src="https://agentmods.dev/badge/skills/stchiotis/library-first-engineering/lfe-boot/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/stchiotis/library-first-engineering/lfe-boot"><img src="https://agentmods.dev/badge/skills/stchiotis/library-first-engineering/lfe-boot.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 | $0.00036 | $0.01090 |
| Opus 5.5 | $0.00014 | $0.00436 |
| Sonnet 5.5 | $0.00007 | $0.00218 |
| Haiku 4.5 | $0.00004 | $0.00109 |
Grade A, and why
lfe-boot 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LFE Session Bootstrap
Protocol
Step 1 — Read the Entrance Card
Read pipeline_status.md. Extract and hold:
- Integrity Score (Verify it is green)
- Active Persona (Architect / Builder / Inspector / Archivist)
- Active Mission (The current goal)
- Pipeline Phase (Which phase and slice we're on)
- Coordination Files (Which steps are complete)
- Session Count (For hygiene scheduling)
Step 2 — Check for Interrupted Session or State Anomaly
Scan .plans/ for coordination files (01_grill_summary.md, 02_prd.md, 03_slices.md, active_plan.md, plan_critique.md, builder_done.md, tdd_report.md, .plans/checks/*, critique.md, inspection_report.md, diagnosis_report.md, hygiene_report.md). Resume mapping per LOOP_ARCHITECTURE.md §4 — the last present file determines the next skill.
-
Scenario A: Normal Interrupted Session If files exist in
.plans/and the entrance card state indicates the mission is in progress:"⚠️ Interrupted session detected. Last completed step: <step>. Resume from: /lfe-<next-skill>. Confirm?"
-
Scenario B: State Anomaly & Zoom-Out Comparison If files exist in
.plans/but the entrance card indicates the mission is complete or ready:- Leave the files in place; clear them only on explicit instruction.
- Invoke the
/lfe-zoom-outskill instructions to perform a high-level comparison: Compare the changes defined in the.plans/files against the current codebase insrc/**. - Inform the user of your findings immediately:
- If the plans match the code:
"⚠️ State Anomaly detected: Files exist in
.plans/but work was already completed and saved tosrc/**. The Archivist missed its cleanup step. Please clear the.plans/directory manually." - If the plans diverge from the code:
"⚠️ State Anomaly detected: Files exist in
.plans/but the changes were not saved to the codebase. This is a real interrupted session."
- If the plans match the code:
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 · 78 lines · 36 tokens per session scan A e98e6f9a10ac
lfe-boot is a skill published in the GitHub repository StChiotis/Library-First-Engineering (46 stars, last pushed 3mo ago), licensed MIT. It adds 36 tokens to every session and 1,090 once invoked, about $0.0001 per session on Opus 5.5. 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
ai-engineering-toolkit
Overview of six AI engineering workflows: prompt evaluation (8-dimension scoring), context budget planning, RAG pipeline design, agent security audit (65-point checklist), eval harness building, and product sense coaching.
promptfoo-provider-setup
Connect Promptfoo to a model, live HTTP API, local Python/JavaScript provider, or app code. Use for request/auth mapping, response parsing, OpenAPI setup, and connection smoke tests. Use promptfoo-evals for broader eval coverage and promptfoo-redteam-setup for attack selection.
avoid-ai-writing
Audit and rewrite content to remove AI writing patterns ("AI-isms"). Use this skill when asked to "remove AI-isms," "clean up AI writing," "edit writing for AI patterns," "audit writing for AI tells," or "make this sound less like AI." Supports a detect-only mode, an edit-in-place mode for files, an optional voice…
prompt-master
Generates optimized prompts for AI tools. Activates only when the user explicitly asks to write, fix, improve, or adapt a prompt for a specific AI tool (LLM, Cursor, Midjourney, image AI, video AI, coding agents, etc.). Does not activate for general conversation, coding tasks, document writing, or other…
voice-preserving-rewriter
Use when the user asks to rewrite, humanize, clean up, or remove AI-isms from text while preserving the writer's voice, facts, intent, structure, register, and protected material.
flux2-lora-training
Plan or review LoRA and edit-training work specifically for FLUX.2 Klein or Qwen-Image-Edit, including paired datasets, trainer-version contracts, and held-out fidelity checks. Do not use for generic Stable Diffusion/DiT training, prompt authoring, or model serving; route those tasks to their specialized skill.