A read-only health check for a Memex workspace, where Memex is a system for organizing notes and project context. It looks for outdated statuses, missing files, conflicting decisions, and mismatches between indexes and files.

Use it to check workspace health and, with its optional fix mode, apply safe annotations to identified problems.

It shows whether the workspace’s organization has drifted or contains stale and inconsistent records.

lint — 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 lint

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/lint/github.svg)](https://agentmods.dev/skills/skyfox-io/memex/lint)

Your own site

<a href="https://agentmods.dev/skills/skyfox-io/memex/lint"><img src="https://agentmods.dev/badge/skills/skyfox-io/memex/lint/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/lint"><img src="https://agentmods.dev/badge/skills/skyfox-io/memex/lint.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 107 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,741 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	$0.00107	$0.02741
Opus 5.5	$0.00043	$0.01096
Sonnet 5.5	$0.00021	$0.00548
Haiku 4.5	$0.00011	$0.00274

Measured 2mo ago against content hash 6b6bed302cf8, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

lint 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 1 executable file (scripts/extract-graph.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/lint/SKILL.md · 236 lines

How it starts

The opening of the file, as written. The whole thing — 236 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Memex - Lint

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

Audit drift and structural integrity, read-only by default. Nine checks, one report.

Step 1: Detect workspace

Run WORKSPACE_ROOT=$(pwd) && echo "$WORKSPACE_ROOT" via Bash, then check for _MANIFEST.md: missing -- "Memex is not initialized. Run /memex:init first." Stop. Present (with or without <!-- memex-managed marker) -- continue.

Step 2: Read manifest

Parse _MANIFEST.md: Tier 1 table (always-loaded files), Tier 2 sections (domain hub references), Tier 3 table (archived files), Hub Map (domain-to-hub mapping).

Resolve paths via: config table (if present) > convention (memory/) > search.

Step 3: Run checks

Run checks in order, collecting WARN (actionable) or INFO (observational) findings.

3.1 Status Freshness

Read status.md's Last updated: YYYY-MM-DD line.

WARN if more than 3 days old (include exact date and day count).
PASS if 3 days or fewer.
WARN if no Last updated line at all.

3.2 Decision Consistency

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

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

Flag each match whose referenced older entry isn't annotated with ~~strikethrough~~.

WARN for each unannotated superseded entry. Include both old and new text.
PASS if no unannotated contradictions found.

Only flag explicit override relationships -- don't infer contradictions from topical similarity.

3.3 Orphan Files

For each domain in the Hub Map:

Source of truth for the domain:
- Closets-only hub (v2.1+): parse <hub-folder>/_CLOSETS.md's ## [[stem]] headings as registered members.
- Legacy hub (with [domain]-index.md): registered = union of the file table's [[wikilinks]] and closets entries.
List all .md files on disk in that domain's folder, excluding the hub index (if any), _CLOSETS.md, and _CLOSETS-archive.md.
Compare.

Read the full file on GitHub · 236 lines

Files

What ships with it

1 file 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.

scripts/extract-graph.py 8.9 KB runs code

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 · 236 lines · 107 tokens per session scan A 6b6bed302cf8

Subscribe to this mod's changes

lint is a skill published in the GitHub repository Skyfox-io/Memex (17 stars, last pushed 4mo ago), licensed MIT. It adds 107 tokens to every session and 2,741 once invoked, about $0.0004 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.

Debugging anthropic claude claude-cowork claude-cowork-plugin obsidian obsidian-md

lint next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
lintSkyfox-io/Memex	Skill	17	4mo ago	MIT	A	107	Claude Code
Diagnosewrg32786/aigent-os	Skill	24	yesterday	MIT	A	57	Claude Code, Codex
First 10 Moveswrg32786/aigent-os	Skill	24	yesterday	MIT	A	57	Claude Code, Codex
Stuckwrg32786/aigent-os	Skill	24	yesterday	MIT	A	46	Claude Code, Codex
learn-from-failurewrg32786/aigent-os	Skill	24	yesterday	MIT	A	0	Claude Code, Codex
solution-huntwrg32786/aigent-os	Skill	24	yesterday	MIT	A	0	Claude Code, Codex
system-checkwrg32786/aigent-os	Skill	24	yesterday	MIT	A	31	Claude Code