lfe-archivist

A command that acts as the Archivist in an LFE-compliant project. LFE is a project workflow with defined stages and coordination rules.

In plain words
What is it for?
Use it to update documentation, changelogs, and pipeline status after a change has been approved.
Why use it?
It keeps documentation and project records synchronized after an approved change, while preventing the command from running at the wrong workflow stage.

Command for Claude Code

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.

agentmods
npx agentmods add commands/stchiotis/library-first-engineering/lfe-archivist
Clone the repo
git clone --depth 1 https://github.com/StChiotis/Library-First-Engineering

Made for: Claude Code.

Per session 40 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 197 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 88% copy Near-identical to another mod 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 $0.00040 $0.00197
Opus 5 $0.00020 $0.00098
Sonnet 5 $0.00008 $0.00039
Haiku 4.5 $0.00004 $0.00020

Measured 3d ago against content hash f82be4477fbf, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

lfe-archivist 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.

Origin

This is a copy

88% identical to lfe-architect — 8 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.claude/commands/lfe-archivist.md · 9 lines

What it actually says

Generated pointer — not the protocol. This command exists so /lfe-archivist dispatches natively in Claude Code. The canonical skill lives at .agents/skills/lfe-archivist/SKILL.md (LFE-SOURCE).

Read .agents/skills/lfe-archivist/SKILL.md now and execute its protocol exactly as written — including its position-in-pipeline preconditions and its coordination-file contract. Honor the Skill Invocation Authority rules (LLM_AGENT_GUIDE §8.8): if this skill is agent-dispatched only and was typed out of sequence, refuse and route through the assembly line. Any change to skill behavior belongs in the canonical file, never in this pointer.

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. 3d ago First seen · 9 lines · 40 tokens per session scan A f82be4477fbf

Subscribe to this mod's changes

lfe-archivist is a command published in the GitHub repository StChiotis/Library-First-Engineering (43 stars, last pushed 1mo ago), licensed MIT. It adds 40 tokens to every session and 197 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 88% identical to lfe-architect, differing in 8 lines, and is treated as a copy.