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-archivistnpx skills add StChiotis/Library-First-Engineering --skill lfe-archivistgit 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-archivist)<a href="https://agentmods.dev/skills/stchiotis/library-first-engineering/lfe-archivist"><img src="https://agentmods.dev/badge/skills/stchiotis/library-first-engineering/lfe-archivist.svg" alt="Measured on agentmods" 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 | $0.00040 | $0.02865 |
| Opus 5 | $0.00020 | $0.01432 |
| Sonnet 5 | $0.00008 | $0.00573 |
| Haiku 4.5 | $0.00004 | $0.00286 |
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 4d 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LFE Archivist
Mission
Keep the project's documentation and history perfectly in sync with the codebase. You are the "Guardian of Truth" who ensures the Library System remains reliable.
Sub-Pipeline (execute in this order)
/lfe-archivist(this skill) → Sync docs, update CHANGELOG, update pipeline_status.md- Check: More slices? → Yes: loop back to Architect for next slice. No: proceed to cleanup.
- Cleanup → Archive/delete coordination files from
.plans/ - Check: Hygiene due? (5+ sessions since last sweep) → If yes, recommend
/lfe-hygiene
Toolbox
/lfe-to-issues: Use to create follow-up issues for deferred work or technical debt.
Hard Rules
- Library System Hierarchy: Maintain the three-layer documentation structure (Entrance Card → Floor Map → Shelf Index).
- CHANGELOG Rolling Window (HARD): keep
CHANGELOG.mdat 7 milestones or fewer; move the oldest to an archive file. - Index Sync: Every ADR or documentation change requires updating the relevant index tables.
- No Behavior Changes: You only touch documentation and planning artifacts.
- File-Based Input: Read
.plans/inspection_report.mdas input. The Inspector's report tells you what passed. - Retention scope: Walking the full Retention Policy table is the Hygiene step's job (every 5 sessions), not the per-mission Archivist's. The Archivist only enforces the CHANGELOG rolling window inline; everything else (
architecture-decisions.md,PROTOCOL_DEBT.md,known-issues.md) is swept by/lfe-hygiene. - Prose-not-literal doc-writing discipline: When you write or update documentation (CHANGELOG entries, ADRs, known-issues entries, Floor Map rows) that describes a search-pattern-based AC or check, describe the pattern in words rather than reproducing the literal search/regex string. Reproducing a pattern in a doc re-triggers that pattern's own check the next time it runs. This mirrors the discipline already in the Architect's Plan-Composition Discipline.
- Entrance-card budget (HARD): keep
pipeline_status.mdwithin the entrance-card retention rule (GOVERNANCE.md§ Retention Policy) — ≤ 12,000 chars total (> 10,000 = act now); the table cells hold the current mission only behind a leading legal[STATE]token; theActive Personacell carries the bare persona name; at most 3 one-line pointers under## 📜 Recent Missions; mission history lives inCHANGELOG.md(whose Step-3 write this rule depends on) — the card carries pointers only. Enforced by the verify-then-trim procedure in Step 6. A platform distribution may additionally mechanize this rule as a validator or hook (GOVERNANCE.md§ Discipline Gates); the agnostic core keeps it as a discipline.
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.
- 4d ago First seen · 91 lines · 40 tokens per session scan A eada449439c5
lfe-archivist is a skill 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 2,865 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.
Other skills, from other repositories
release-checklist
Minimal release checklist used as the control variant.
playwright
Use when the task requires capturing or automating a real browser from the terminal.
implementation-final-review
Perform the repository's risk-tiered independent final review before implementation completion. Use only when explicitly invoked or when repository instructions require it after behavior-impacting implementation work; audit the complete task diff, supported contracts, lifecycle and security boundaries, complexity, and…
promptfoo-provider-setup
Configure promptfoo providers or redteam targets for hosted models, live HTTP APIs, Python/JavaScript local scripts, agent SDKs, or multi-input systems. Use when connecting promptfoo to the system under test, mapping vars, auth env vars, request bodies, response transforms, or static-code-derived provider wrappers. Do…
search-params
URL search param and hash state management. Use when adding or modifying URL search params, working with useSearchParams, setSearchParams, useSearchParamState, or navigate() with query strings or hash fragments, or fixing browser back/forward button issues.
split-commit-into-stack
Split one oversized commit or branch into a stack of independently reviewable Graphite (gt) PRs - deciding what genuinely separates, what is atomic and must stay whole, and proving each lower PR builds and passes without the ones above it. Use when asked to "split this PR", "this commit is too big", "break this into a…