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 skills/stchiotis/library-first-engineering/lfe-sessionnpx skills add StChiotis/Library-First-Engineering --skill lfe-sessiongit clone --depth 1 https://github.com/StChiotis/Library-First-EngineeringWhat 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 | $0.00069 | $0.04556 |
| Opus 5 | $0.00034 | $0.02278 |
| Sonnet 5 | $0.00014 | $0.00911 |
| Haiku 4.5 | $0.00007 | $0.00456 |
Grade A, and why
lfe-session 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 3d 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 — 240 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LFE Framework Improvement Session
You are acting as a senior framework architect helping improve the Library-First Engineering (LFE) framework. This is a META session — you are working ON the framework, not WITH it. Do NOT run the LFE pipeline (/lfe-boot, /lfe-architect, etc.) — those are for product repos that use LFE as a template.
Source of truth for framework state: GitHub Issues + git history. NOT the .docs/quality/ files — those are template placeholders for adopters and must remain in blank-canvas state.
Orientation Protocol
Execute these steps in order. Be concise — present findings, not narration.
Step 1 — Framework Identity Snapshot
Establish what the framework currently is (as opposed to what it's tracking):
- Read
README.md— extract claimed counts (skills, personas, pillars). These are public-facing assertions and must match reality. - Read
LLM_AGENT_GUIDE.md§9 — the canonical skill table. - Count
.agents/skills/*/SKILL.mdfiles — should match the claimed count. - Note current branch + active feature branches:
!git branch --show-current && git branch -a 2>/dev/null | head -20
Step 2 — Open Work Surface (GitHub Issues + PRs)
Framework work is tracked exclusively on GitHub. Read both issues and open PRs:
!gh issue list --limit 25 --json number,title,labels,updatedAt --jq '.[] | "#\(.number) [\(.labels | map(.name) | join(", "))] \(.title)"' 2>/dev/null || echo "GH unavailable"
!gh pr list --limit 10 --json number,title,isDraft,labels --jq '.[] | "PR #\(.number)\(if .isDraft then " (draft)" else "" end) [\(.labels | map(.name) | join(", "))] \(.title)"' 2>/dev/null || echo "No PRs"
Step 3 — Recent Activity
!git log --oneline -15 2>/dev/null || echo "No git history"
Step 4 — Structural Integrity Test Suite
Run these 12 tests. For each, output PASS / FAIL: . Failures become candidate focus areas in the briefing.
T1. Pipeline status canvas. pipeline_status.md exists. Mission State is [BLANK CANVAS]. All 9 coordination checkboxes present (01 02 03 plan plan_critique build tdd critique inspect). Session count is 0. Last sweep is none yet.
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.
- 3d ago First seen · 240 lines · 69 tokens per session scan A ead5b1cef52b
lfe-session is a skill published in the GitHub repository StChiotis/Library-First-Engineering (43 stars, last pushed 1mo ago), licensed MIT. It adds 69 tokens to every session and 4,556 once invoked, about $0.0003 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 skills, from other repositories
context-engineering
Manages agent context for effective AI-assisted development. Use when working on large codebases, when the agent seems to lack necessary context, when structuring CLAUDE.md or project guidance files, or when coordinating long multi-step development sessions.
GuoFanDirector_Skills
郭帆导演风格视听语言体系，涵盖分镜设计、场景气氛、预演动态等导演工作流知识.
embedded-captions
Add captions or subtitles to an existing single-subject talking-head video without editing the footage. Use for plain verbatim captions, cinematic captions embedded behind the subject, VFX captions, “炸/特效/酷炫字幕,” or a named identity from the 35-style catalog. Route by visual identity, not by backend engine. The quiet…
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
happiness-skill
当用户问「怎么才能更幸福/为什么得到了还不满足/怎么减少焦虑」时调用。 核心理念: 幸福是缺憾感清空的默认状态, 是可训练的技能; 欲望是与自己的契约(得到前不快乐), 同时只留一个重大欲望; 活在当下。 不适用于: 临床抑郁等需要专业治疗的场景(本书方法不能替代医疗)。 Triggers: 幸福/不快乐/欲望/焦虑/知足/活在当下/happiness/desire/anxiety.
docx-comment-reply
Reply to comments (批注) in Word .docx/.doc files: extract comment context, draft replies, write threaded replies back, and validate OOXML.