clean-claude-memory

A guide for reviewing Claude Code's project memory: notes stored outside a repository for use in later sessions. It checks the memory index and its topic files against the current project.

In plain words
What is it for?
Use it to audit, remove, rewrite, or reorganize project memory and rebuild MEMORY.md.
Why use it?
Memory notes can become outdated, duplicated, or incorrect, so they may cause future coding sessions to make wrong assumptions.

Skill for Claude CodeCodex

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/heapy/kortex/clean-claude-memory
Any agent
npx skills add Heapy/kortex --skill clean-claude-memory
Clone the repo
git clone --depth 1 https://github.com/Heapy/kortex

Made for: Claude Code, Codex.

Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 710 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 $0.00047 $0.00710
Opus 5 $0.00023 $0.00355
Sonnet 5 $0.00009 $0.00142
Haiku 4.5 $0.00005 $0.00071

Measured 2d ago against content hash ed072b714edf, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

clean-claude-memory 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 2d 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.

plugins/heapy/skills/clean-claude-memory/SKILL.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Clean Claude Memory

Claude Code stores project-scoped durable notes outside the repository:

~/.claude/projects/<encoded-absolute-project-path>/memory/

MEMORY.md is the index. Other Markdown files are topic memories. Memory is a hint for future sessions, not an authoritative source; verify every claim against current code, docs, configuration, tools, and project state.

Treat recorded plans as historical artifacts only, not as documentation or a source of truth. Never use them to implement other features or as authoritative evidence about current behavior; verify relevant claims against current code, tests, configuration, requirements, and project documentation.

Do not include these unless the user explicitly expands the scope:

  • repository CLAUDE.md or AGENTS.md;
  • global ~/.claude/CLAUDE.md;
  • memories belonging to another project.

Workflow

  1. Resolve the current project's memory directory.
  2. Read MEMORY.md and inventory every sibling memory file.
  3. Review topic files one at a time. For each file:
    • read it completely;
    • explain what it preserves;
    • verify its claims against current authoritative sources;
    • identify stale facts, duplication, historical narration, and transient paths, versions, plans, or commands;
    • recommend one action;
    • ask the user one direct question and wait before reviewing the next file.

Use these actions:

Action Use when
Keep Unique, durable intent or preference remains accurate and useful.
Rewrite A valuable core remains, but the file contains stale or excessive detail.
Delete The content is obvious, obsolete, historical, or already authoritative elsewhere.
Move The information belongs in code, tests, docs, a backlog task, or a reusable skill.

For Move, create and verify the new home before deleting the memory:

  • code invariant or non-obvious trade-off → nearby comment or test;
  • actionable future work → project task or issue;
  • durable project contract → project documentation;
  • reusable agent workflow → skill.

Read the full file on GitHub · 79 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.

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. 2d ago First seen · 79 lines · 47 tokens per session scan A ed072b714edf

Subscribe to this mod's changes

clean-claude-memory is a skill published in the GitHub repository Heapy/kortex (6 stars, last pushed 4d ago), licensed Apache-2.0. It adds 47 tokens to every session and 710 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 2026-08-31.

Related

Other skills, from other repositories

mobile-experience-report

Use when the user says 'my site looks bad on mobile', 'check mobile layout', 'responsive audit', or 'site broken on phones'. Diagnoses breakpoint problems, text sizing, column stacking failures, hidden elements, and navigation menu behavior, device by device.

respira-press/agent-skills-wordpress · 58 tokens

motherduck-design-dive

Design or redesign a MotherDuck Dive as a responsive, reusable analytics interface. Use when a Dive must be mobile-friendly from the start, support light and dark modes, reserve space for filters, use restrained Power BI-style information design, embed small charts inside metric components, or work across customers…

motherduckdb/agent-skills · 69 tokens

desktop-expert

Compose Multiplatform Desktop patterns for the desktopApp/ module. Use when working with (1) Desktop-only APIs (Window, WindowState, Tray, MenuBar, Dialog), (2) keyboard shortcuts and menu systems with OS-aware conventions (Cmd vs Ctrl, isMacOS branching), (3) desktop navigation (NavigationRail/sidebar vs Android…

vitorpamplona/amethyst · 157 tokens

gradle-expert

Build optimization, dependency resolution, and multi-module KMP troubleshooting for AmethystMultiplatform. Use when working with: (1) Gradle build files (build.gradle.kts, settings.gradle), (2) Version catalog (libs.versions.toml), (3) Build errors and dependency conflicts, (4) Module dependencies and source sets, (5)…

vitorpamplona/amethyst · 132 tokens

add-native

Public entry point for native device capabilities and native controls — camera, image picker, barcode/QR scanner, document picker, file picker, secure storage, file system, sharing, PDF generation/viewing, pen/signature capture, background GPS/geolocation tracking, or supported local file workflows — in a Power Apps…

microsoft/power-platform-skills · 96 tokens

amy-expert

Patterns for extending amy, the Amethyst CLI in cli/. Use when adding an amy command, touching files under cli/src/main/kotlin/…/cli/, wiring a new subcommand into Main.kt, writing an interop test script that drives Amy, or extracting logic out of amethyst/ into commons/ so a CLI command can call it. Enforces the…

vitorpamplona/amethyst · 217 tokens