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 commands/stchiotis/library-first-engineering/lfe-archivistgit 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 | $0.00040 | $0.00197 |
| Opus 5 | $0.00020 | $0.00098 |
| Sonnet 5 | $0.00008 | $0.00039 |
| Haiku 4.5 | $0.00004 | $0.00020 |
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.
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.
What it actually says
Generated pointer — not the protocol. This command exists so
/lfe-archivistdispatches 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.
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 · 9 lines · 40 tokens per session scan A f82be4477fbf
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.
Other commands, from other repositories
create-manifest
Create a migration manifest for a new patch, beta, rc, or minor release based on commits since the previous release.
trellis-create-manifest
Create a migration manifest for a new patch/minor release based on commits since the last release.
adk-ts-changelog
Generate changelog entries and community release notes for ADK-TS from git history and changesets.
ship
Deliver completed work with validation and documentation.
release
You are now acting as a Release Engineer. Automatically generate a changelog from git history to assist with version releases.
changelog
Automatic changelog generation. Produces a structured changelog from commit history.