memory-clean

A report-first audit for a coding agent's memory files, checking their structure, references, duplicates, missing sections, size, and staleness against session records.

In plain words
What is it for?
Use it to find orphaned or duplicate memories, broken references, oversized entries, missing content, and information that no longer matches past sessions.
Why use it?
It identifies outdated or damaged memory entries without changing them until the user confirms the proposed fixes.

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/outlinedriven/odin-codex-plugin/memory-clean
Any agent
npx skills add OutlineDriven/odin-codex-plugin --skill memory-clean
Clone the repo
git clone --depth 1 https://github.com/OutlineDriven/odin-codex-plugin

Made for: Claude Code, Codex.

Per session 62 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 972 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 $0.00062 $0.00972
Opus 5 $0.00031 $0.00486
Sonnet 5 $0.00012 $0.00194
Haiku 4.5 $0.00006 $0.00097

Measured 2d ago against content hash ba5c3006a320, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

memory-clean 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.

The scan reads SKILL.md. This mod also ships 3 executable files (scripts/audit-memory.sh, scripts/encode-memory-path.sh, scripts/resolve-paths.sh), 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

skills/memory-clean/SKILL.md · 99 lines

How it starts

The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Audit memory for structural rot and staleness, report with evidence, fix only on user confirmation.

Scope

Audits and fixes existing memory files. Does not create new memories from session signals (that is memory-update). Does not redact PII or credentials (that is memory-sanitize, which memory-clean will recommend when it detects suspected credentials at critical severity).

Path resolution

Scripts live under this skill's own scripts/ directory. Resolve the skill root from $HOME (the conventional install path is $HOME/.claude/claude/skills/memory-clean/):

SKILL_SCRIPTS="${MEMORY_CLEAN_SKILL_SCRIPTS:-$HOME/.claude/claude/skills/memory-clean/scripts}"
MEMORY_DIR=$("$SKILL_SCRIPTS/resolve-paths.sh" memory_dir)
SESSION_HISTORY_GLOB=$("$SKILL_SCRIPTS/resolve-paths.sh" session_history_glob)

Set MEMORY_CLEAN_SKILL_SCRIPTS to override when the skill is installed outside $HOME/.claude. Abort on non-zero exit from the resolver. Overrides via MEMORY_DIR / SESSION_HISTORY_GLOB env vars.

Workflow

1. Resolve paths (above)

2. Snapshot before any fix

cp -r "$MEMORY_DIR" /tmp/memory-snapshot-$(date +%s)

Never mutate originals without a snapshot.

3. Run structural audit

./scripts/audit-memory.sh "$MEMORY_DIR" "$SESSION_HISTORY_GLOB" > /tmp/memory-audit-$(date +%s).json

The script emits JSON with these arrays:

Field What it detects
orphans Files in dir with no MEMORY.md entry
dangling MEMORY.md entries pointing to missing files
near_duplicates File pairs with >70% content overlap
structural Missing frontmatter, missing Why:/How to apply:, index line > 150 chars, MEMORY.md > 200 lines, type-mismatch, fix-recipe content
staleness Memories whose stated rule conflicts with recent session evidence

Read references/AUDIT-CHECKLIST.md for full detection rules per category.

4. Render report grouped by severity

CRITICAL (N)
  [cred-scan] feedback_no-html-comments.md — suspected credential on line 7
  → Recommend: run memory-sanitize first

WARN (N)
  [near-dup] feedback_consistent-config.md ↔ feedback_no-html-comments.md (82% overlap)
  [stale] feedback_bump-minor-versions.md — rule contradicted in 4 recent sessions
    Evidence: turns uuid-aaa, uuid-bbb, uuid-ccc, uuid-ddd

INFO (N)
  [orphan] user_role_data_scientist.md — not in MEMORY.md index
  [index-long] project_auth-rewrite.md — index entry is 163 chars (limit 150)

Read the full file on GitHub · 99 lines

Files

What ships with it

5 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.

  1. 2d ago First seen · 99 lines · 62 tokens per session scan A ba5c3006a320

Subscribe to this mod's changes

memory-clean is a skill published in the GitHub repository OutlineDriven/odin-codex-plugin (15 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 62 tokens to every session and 972 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

apm-review-panel

Use this skill to run a multi-persona expert advisory review on a labelled pull request in microsoft/apm. The panel fans out to five mandatory specialists plus a test-coverage specialist (active on every PR that touches src/) plus three conditional specialists (auth, doc-writer, performance-expert), all running in…

microsoft/apm · 178 tokens

batch-bug-shepherd

Use this skill to drive a batch of suspected bugs in microsoft/apm from raw issue list to mergeable PR queue. Fan out one triage subagent per issue (LEGIT / UNCLEAR / FIXED-AT-HEAD), gate every legit bug against PRINCIPLES.md via an apm-ceo strategic-alignment pass, cross-reference legit issues against open PRs, then…

microsoft/apm · 227 tokens

apm-spec-guardian

Use this skill to run a four-panel adversarial advisory review on any pull request that touches the OpenAPM specification artifact (docs/src/content/docs/specs/openapm-.md), its inline / sidecar JSON Schemas (docs/src/content/docs/specs/schemas/.schema.json), or the conformance fixture seed…

microsoft/apm · 215 tokens

apm-triage-panel

Use this skill to triage one microsoft/apm issue selected by the daily sweep, the status/needs-triage fast path, or manual dispatch. Emit one synthesized comment with a decision, label set, exact milestone, and suggested next action.

microsoft/apm · 59 tokens

cli-logging-ux

Use this skill when editing or creating CLI output, logging, warnings, error messages, progress indicators, or diagnostic summaries in the APM codebase. Activate whenever code touches console helpers (richsuccess, richwarning, richerror, richinfo, richecho), DiagnosticCollector, STATUSSYMBOLS, CommandLogger, or any…

microsoft/apm · 94 tokens

pr-description-skill

Use this skill to write the PR description (PR body) for any pull request opened against microsoft/apm. Produces one self-sufficient GitHub-Flavored Markdown artifact: TL;DR, Problem (WHY), Approach (WHAT), Implementation (HOW), 1-3 validated mermaid diagrams, explicit trade-offs, validation evidence, and a…

microsoft/apm · 131 tokens