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.
npx skills add OutlineDriven/odin-codex-plugin --skill memory-cleangit clone --depth 1 https://github.com/OutlineDriven/odin-codex-pluginWrote 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.
[](https://agentmods.dev/skills/outlinedriven/odin-codex-plugin/memory-clean)<a href="https://agentmods.dev/skills/outlinedriven/odin-codex-plugin/memory-clean"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-codex-plugin/memory-clean/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.
<a href="https://agentmods.dev/skills/outlinedriven/odin-codex-plugin/memory-clean"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-codex-plugin/memory-clean.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00062 | $0.00972 |
| Opus 5.5 | $0.00025 | $0.00389 |
| Sonnet 5.5 | $0.00012 | $0.00194 |
| Haiku 4.5 | $0.00006 | $0.00097 |
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 1mo 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- memory-clean — 100% identical, 0 lines differ
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)
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.
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.
- 1mo ago First seen · 99 lines · 62 tokens per session scan A ba5c3006a320
memory-clean is a skill published in the GitHub repository OutlineDriven/odin-codex-plugin (14 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 62 tokens to every session and 972 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.
Other skills, from other repositories
memory-clean
Audit memory directory for structural issues (orphans, dangling refs, duplicates, missing sections, oversized entries) and staleness against session-history transcripts; report-first, fix-on-confirmation. Use when the user says "audit memory", "memory hygiene", or "find stale/duplicate memories".
memory-update
Scan agent's session-history transcripts for save-worthy signals (corrections, preferences, decisions, references), propose and write auto-memory files with valid frontmatter and MEMORY.md entry. Use when the user says "save this to memory", "remember that", or "scan this session for memories".
memory-sanitize
Produce share-safe copies of memory files under /tmp with PII redacted (paths, emails, session IDs, dates) and credentials scanned (tokens, keys); never mutates originals. Use when the user says "sanitize memory for sharing", "redact memory PII", or "scan memory for credentials".
corral
Query local Claude Code, Codex CLI, OpenCode, Kimi Code CLI, Cursor Agent CLI, and Pi session history through the corral CLI — list recent sessions, search by topic, read a session's conversation, export a shareable transcript with tool calls and thinking, or build a handoff context package to continue interrupted…
studio-context-brief
Use when an active KIT-managed Goal needs compact brief, working, or resume context projections from trusted structured state while preserving exact technical literals and durable handoff authority.
cass
Mine past agent sessions for working prompts, decisions, and patterns. Use when "what did I ask?", "find that prompt", session archaeology, or agent history.