archive

archive is a skill for Claude Code, Codex from Skyfox-io/Memex. It costs 57 tokens per session (718 once invoked), scanned A, original, MIT.

A workspace filing action that marks a file as archived in Memex, a system for organizing notes and project context. The file remains on disk but is no longer loaded automatically.

In plain words
What is it for?
Use it to move a file from the active Tier 2 list to the archived Tier 3 list and update Memex’s tracking records.
Why use it?
It keeps old, wrapped, or replaced material from cluttering the context loaded for new work.

Skill for Claude CodeCodex

Part of the memex plugin — 17 skills shipped together

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 skills/skyfox-io/memex/archive
Any agent
npx skills add Skyfox-io/Memex --skill archive
Clone the repo
git clone --depth 1 https://github.com/Skyfox-io/Memex

Made for: Claude Code, Codex.

Or install memex, the plugin that ships this one along with the rest of its 17 skills.

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 archive

README.md
[![agentmods](https://agentmods.dev/badge/skills/skyfox-io/memex/archive.svg)](https://agentmods.dev/skills/skyfox-io/memex/archive)
Your own site
<a href="https://agentmods.dev/skills/skyfox-io/memex/archive"><img src="https://agentmods.dev/badge/skills/skyfox-io/memex/archive.svg" alt="Measured on agentmods" height="20"></a>
Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 718 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00057 $0.00718
Opus 5 $0.00028 $0.00359
Sonnet 5 $0.00011 $0.00144
Haiku 4.5 $0.00006 $0.00072

Measured 4d ago against content hash 19aac9dd608f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

archive 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.

memex/skills/archive/SKILL.md · 64 lines

How it starts

The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Memex - Archive

Wikilink rule: Use [[filename]] for every file reference in markdown.

Move a file from Tier 2 to Tier 3 in _MANIFEST.md and update its hub status. The file stays on disk; archiving just stops auto-loading.

Step 1: Find workspace root

Run WORKSPACE_ROOT=$(pwd) && echo "$WORKSPACE_ROOT" via Bash.

Read _MANIFEST.md. If missing: tell the user "No manifest found. Run /memex:init first." and stop.

Step 2: Identify the file

If $ARGUMENTS is set, use it. Otherwise read the Tier 2 sections from _MANIFEST.md, show the entries, and ask which to archive.

Step 3: Move in manifest

  1. Remove the file's row from its Tier 2 domain section.
  2. Add to the Tier 3 table with today's date and a brief reason:
| [[filename]] | [why archived] | YYYY-MM-DD |

Step 4: Update the hub and closets

Read the relevant domain hub. Set the file's status to Archived, or remove it from the active table.

Then update the file's entry in <domain>/_CLOSETS.md (or _CLOSETS-archive.md if it lives there per pagination). Change the entry's status: line to status: archived. If the file has no closets entry yet, skip. Session-end will not re-create it for an archived file.

Closets schema and field semantics: memex/skills/session-end/references/closets-format.md.

Step 5: Confirm

Archived: [filename]
  From:   Tier 2 ([domain name])
  Reason: [why]
  Date:   YYYY-MM-DD

To unarchive: move the row back to Tier 2 in _MANIFEST.md.

Gotchas

  • Archive is a manifest move, not a file deletion. The file stays on disk. Don't rm it. Don't move it to an archive/ folder unless the user explicitly asks. That breaks existing wikilinks.
  • Tier 3 entries still need wikilinks. Use [[filename]] in the Tier 3 row so the Obsidian graph keeps the node connected.
  • Don't strip the closets entry. The file's _CLOSETS.md entry stays, with status: archived. Future searches still surface it, just at lower priority.
  • Tier 1 files don't archive. status.md, decisions.md, glossary.md, etc. are always-loaded by design. Refuse and explain.
  • Reason is load-bearing. Examples: "wrapped", "superseded by [[new-file]]", "stale". Future you reads this when deciding whether to unarchive. "no longer needed" is not a reason.

Read the full file on GitHub · 64 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. 4d ago First seen · 64 lines · 57 tokens per session scan A 19aac9dd608f

Subscribe to this mod's changes

archive is a skill published in the GitHub repository Skyfox-io/Memex (17 stars, last pushed 2mo ago), licensed MIT. It adds 57 tokens to every session and 718 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.

Related

Other skills, from other repositories

wage-hour-qa

Jurisdiction-aware pay and working time Q&A — NMW/NLW compliance, overtime, rest breaks, holiday pay calculation, final pay, and employment status for pay purposes — answered for the specific jurisdiction with the controlling rule researched and cited rather than stated from memory. Use when the user asks any pay or…

uk-agents/uk-legal-plugins · 111 tokens

obsidian-companion

Use when interacting with the user's Obsidian vault — reading, writing, searching, or chatting with notes using local RAG. Guides tool selection and writing strategy for all vault operations.

thoreinstein/obsidian-rag · 42 tokens

wiki-ingest

Use when the user wants to ingest external sources into the vault — PDFs, markdown files, transcripts, Readwise exports, or any document. Triggers on "ingest", "process document", "import into vault", "distill this", "add to vault", or "extract knowledge from".

thoreinstein/obsidian-rag · 64 tokens

vault-lint

Use when the user wants a health audit of the vault — stale content, provenance drift, frontmatter compliance, or MOC coverage gaps. Triggers on "lint vault", "vault health", "check vault", "stale notes", "vault audit", "vault quality", or "check conventions".

thoreinstein/obsidian-rag · 65 tokens

compound

Use when the user wants to promote cross-project knowledge to the global Engineering/ folder, or says "promote knowledge", "compound notes", "knowledge synthesis", or "find repeated ideas across projects".

thoreinstein/obsidian-rag · 42 tokens

links

Use when the user wants to explore connections between notes, see what links to or from a note, or says "links", "backlinks", "connections", or "graph".

thoreinstein/obsidian-rag · 38 tokens