A maintenance command that checks a Memex workspace for duplicate files, conflicting decisions, unused files, and oversized decision logs. It can also add safe annotations when asked.

Use it for periodic workspace audits and to identify files that may need merging, clarification, archiving, or cleanup.

It finds information-management drift that normal session cleanup does not cover, while leaving files unchanged by default.

consolidate — Skill for Claude Code by Skyfox-io/Memex

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 Skyfox-io/Memex --skill consolidate

Clone the repo

git clone --depth 1 https://github.com/Skyfox-io/Memex

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/skyfox-io/memex/consolidate/github.svg)](https://agentmods.dev/skills/skyfox-io/memex/consolidate)

Your own site

<a href="https://agentmods.dev/skills/skyfox-io/memex/consolidate"><img src="https://agentmods.dev/badge/skills/skyfox-io/memex/consolidate/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/skyfox-io/memex/consolidate"><img src="https://agentmods.dev/badge/skills/skyfox-io/memex/consolidate.svg" alt="Reviewed on agentmods" width="80" 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 1,959 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.

Model	Per session	Once invoked
Fable 5.1	$0.00057	$0.01959
Opus 5.5	$0.00023	$0.00784
Sonnet 5.5	$0.00011	$0.00392
Haiku 4.5	$0.00006	$0.00196

Measured 2mo ago against content hash 72834cf03d11, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

consolidate 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 2mo ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/extract-graph.py, scripts/verify-wikilinks.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/consolidate/SKILL.md · 178 lines

How it starts

The opening of the file, as written. The whole thing — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Memex - Consolidate

Wikilink rule: When referencing any file in markdown, always use [[filename]] wikilink format.

Independent drift sweep that session-end deliberately doesn't do. Four phases run in order: dedup, decisions contradictions, orphans, decisions compression. Read-only by default; --fix only applies safe annotations.

Step 0: Detect workspace and acquire lock

Run WORKSPACE_ROOT=$(pwd) && echo "$WORKSPACE_ROOT" via Bash. Confirm _MANIFEST.md exists; if not, tell the user to run /memex:init and stop.

Acquire memory/.consolidate.lock and check the 24-hour cooldown in memory/.consolidate-runs.log. Both follow the shared bulk-write convention. See references/locking.md.

Step 1: Dedup

Detect candidate duplicate files:

List all .md files in domain folders. Skip memory/, scratch/, .git, .obsidian, .claude, memex.
Group files where:
- Filename stems are similar (Levenshtein distance ≤ 2 on lowercase stems), OR
- Top wikilinks (the 5 most frequent [[targets]] cited inside) overlap by ≥ 80%.
For each group of ≥ 2 candidates, list: file path, file size, last-modified date, one-line summary of subject overlap.

Output but do not auto-merge. Dedup is user-confirmed always. --fix does not auto-merge files.

Step 2: Decisions contradiction sweep

Read decisions.md. Scan newer entries for explicit override language referencing earlier entries:

supersedes, replaces, dropped, no longer, instead of, reverses, overrides

For each match:

Find the older entry being referenced (string-match on the topic).
Check whether it's already annotated with ~~strikethrough~~ and (superseded YYYY-MM-DD).

If unannotated:

Show the pair: old entry text, new entry text.
Suggest: "Annotate the old entry with strikethrough and a (superseded <date>) marker."

With --fix: Apply the strikethrough + supersession marker automatically. Same logic as /memex:lint --fix's decision-consistency annotation.

Read the full file on GitHub · 178 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

2mo ago First seen · 178 lines · 57 tokens per session scan A 72834cf03d11

Subscribe to this mod's changes

consolidate is a skill published in the GitHub repository Skyfox-io/Memex (17 stars, last pushed 4mo ago), licensed MIT. It adds 57 tokens to every session and 1,959 once invoked, about $0.0002 per session on Opus 5.5. 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.

Memory and context anthropic claude claude-cowork claude-cowork-plugin obsidian obsidian-md

consolidate next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
consolidateSkyfox-io/Memex	Skill	17	4mo ago	MIT	A	57	Claude Code
setup-brainmycelium-hq/ai-brain-starter	Skill	50	yesterday	MIT	A	66	Claude Code
second-brain-mappingmycelium-hq/ai-brain-starter	Skill	50	yesterday	MIT	A	116	Claude Code
evolvemycelium-hq/ai-brain-starter	Skill	50	yesterday	MIT	A	100	Claude Code
closewrg32786/aigent-os	Skill	24	yesterday	MIT	A	15	Claude Code
dreamwrg32786/aigent-os	Skill	24	yesterday	MIT	A	25	Claude Code
Promotewrg32786/aigent-os	Skill	24	yesterday	MIT	A	68	Claude Code, Codex