lfe-whats-next

lfe-whats-next is a skill for Claude Code, Codex from StChiotis/Library-First-Engineering. It costs 36 tokens per session (603 once invoked), scanned A, original, MIT.

A pipeline-navigation skill that reads project status and coordination files to identify the current phase and the next required action. It is designed for projects whose work is divided into named planning, building, testing, and inspection steps.

In plain words
What is it for?
Use it to check the current project phase, review completed planning or inspection records, and determine the next pipeline step.
Why use it?
It removes guesswork about what has already been completed and which task or skill should run next.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

Good fit Use it to check the current project phase, review completed planning or inspection records, and determine the next pipeline step.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/stchiotis/library-first-engineering/lfe-whats-next
Install

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.

Any agent
npx skills add StChiotis/Library-First-Engineering --skill lfe-whats-next
Clone the repo
git clone --depth 1 https://github.com/StChiotis/Library-First-Engineering

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for lfe-whats-next

README.md
[![agentmods](https://agentmods.dev/badge/skills/stchiotis/library-first-engineering/lfe-whats-next.svg)](https://agentmods.dev/skills/stchiotis/library-first-engineering/lfe-whats-next)
Your own site
<a href="https://agentmods.dev/skills/stchiotis/library-first-engineering/lfe-whats-next"><img src="https://agentmods.dev/badge/skills/stchiotis/library-first-engineering/lfe-whats-next.svg" alt="Measured on agentmods" height="20"></a>
Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 603 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00036 $0.00603
Opus 5 $0.00018 $0.00302
Sonnet 5 $0.00007 $0.00121
Haiku 4.5 $0.00004 $0.00060

Measured 8d ago against content hash 0eca77fa1fcf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

lfe-whats-next 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 8d 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.

.agents/skills/lfe-whats-next/SKILL.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

LFE What's Next

Purpose

Instant orientation. Read the pipeline state and tell the human exactly what step comes next.

Process

1. Read pipeline state

Read pipeline_status.md and extract:

  • Active Persona
  • Active Mission
  • Pipeline Phase
  • Coordination Files status

2. Scan coordination files

Check which files exist in .plans/:

  • 01_grill_summary.md — grill complete?
  • 02_prd.md — PRD complete?
  • 03_slices.md — slices approved?
  • active_plan.md — plan written for current slice?
  • plan_critique.md — pre-build critique verdict? (PASS / WARN / BLOCK)
  • builder_done.md — implementation complete?
  • tdd_report.md — TDD pass complete?
  • .plans/checks/*.md — Inspector sub-skill findings (if enabled)?
  • critique.md — Inspector 4-Eyes pass complete?
  • inspection_report.md — inspection verdict?
  • diagnosis_report.md — bug diagnosis (only on first inspection failure)?

3. Determine next action

Based on what exists and what doesn't, output exactly one block:

📍 Phase <N>: <Phase Name> (Slice <X> of <Y>)
   ✅ Completed: <list of completed steps>
   ⬜ Next step: <exact skill to run>
   🥸 Persona: <who should be active>
   💬 Run: /lfe-<skill-name>

4. Edge cases

No coordination files exist + no active mission:

📍 No active mission.
   💬 Start with: /lfe-boot

Session appears to have crashed mid-pipeline:

📍 ⚠️ Interrupted session detected.
   Last completed: <last file found>
   Resume from: /lfe-<next-skill>
   🥸 Persona: <who should be active>

All slices complete, cleanup pending:

📍 All slices implemented and verified.
   ⬜ Next step: Archivist cleanup
   💬 Run: /lfe-archivist

Hygiene due (session count ≥ 5 since last sweep):

📍 Mission complete.
   ⚠️ Architecture sweep due (5+ sessions since last).
   💬 Run: /lfe-improve-architecture

Rules

  • Never modify any files. This is a read-only skill.
  • Output must be concise — max 5 lines.
  • Use the coordination file presence as ground truth, not conversation context.

Read the full file on GitHub · 79 lines

Changes

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.

  1. 8d ago First seen · 79 lines · 36 tokens per session scan A 0eca77fa1fcf

Subscribe to this mod's changes

lfe-whats-next is a skill published in the GitHub repository StChiotis/Library-First-Engineering (43 stars, last pushed 1mo ago), licensed MIT. It adds 36 tokens to every session and 603 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.

Related

Other skills, from other repositories