agentmods.dev

preserve

preserve is a skill for Claude Code, Codex from sliamh11/Deus. It costs 32 tokens per session (395 once invoked), scanned A, original, MIT.

A memory-maintenance skill that reviews a conversation and saves lasting user preferences, decisions, and useful facts to a permanent memory file.

In plain words
What is it for?
Use it to update long-term agent memory with concise, reusable information.
Why use it?
It keeps important context available across sessions while avoiding temporary or one-off details.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions CLAUDE.md.

not rated 52repo today A scan SkillSpector: pass 32 tokens original MIT

Good fit Use it to update long-term agent memory with concise, reusable information.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/sliamh11/deus/preserve
View source ↗ sliamh11/Deus
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 sliamh11/Deus --skill preserve
Clone the repo
git clone --depth 1 https://github.com/sliamh11/Deus

Made for: Claude Code, Codex.

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.

agentmods badge for preserve

README.md
[![agentmods](https://agentmods.dev/badge/skills/sliamh11/deus/preserve/github.svg)](https://agentmods.dev/skills/sliamh11/deus/preserve)
Your own site
<a href="https://agentmods.dev/skills/sliamh11/deus/preserve"><img src="https://agentmods.dev/badge/skills/sliamh11/deus/preserve/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.

agentmods 80×15 button for preserve

Your own site · 80×15
<a href="https://agentmods.dev/skills/sliamh11/deus/preserve"><img src="https://agentmods.dev/badge/skills/sliamh11/deus/preserve.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 395 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 5.1 $0.00032 $0.00395
Opus 5.5 $0.00013 $0.00158
Sonnet 5.5 $0.00006 $0.00079
Haiku 4.5 $0.00003 $0.00040

Measured 1mo ago against content hash 428e838a5e9f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

preserve 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.

container/skills/preserve/SKILL.md · 41 lines

What it actually says

/preserve — Update Permanent Memory

Silently extract and save lasting knowledge from this conversation to the vault's CLAUDE.md.

The vault is mounted at /workspace/vault/. If it doesn't exist, check /workspace/extra/obsidian/Deus/ as a legacy fallback.

Steps

  1. Read the current CLAUDE.md:

    VAULT_DIR="${DEUS_VAULT_DIR:-/workspace/vault}"
[ ! -d "$VAULT_DIR" ] && VAULT_DIR="/workspace/extra/obsidian/Deus"
cat "$VAULT_DIR/CLAUDE.md"
wc -l "$VAULT_DIR/CLAUDE.md"

  2. Review the conversation — identify what's genuinely worth permanent memory:

    • User preferences or habits revealed
    • Facts about the user (schedule, people, places, situations)
    • Decisions with lasting effect
    • Things the user corrected or clarified
    • Recurring patterns worth anticipating

    Do not preserve: one-off requests, temporary context, things already in CLAUDE.md.

  3. Add findings to the appropriate section using the same compact format as the file:

    • Use key: value shorthand, not prose bullets
    • One line per insight
    • Write as data, not narrative

  4. Auto-archive if file exceeds 200 lines:

    • Move completed projects and old decisions to $VAULT_DIR/CLAUDE-Archive.md
    • Keep core blocks: identity line, tools, projects, pending, decisions

  5. Confirm briefly what was added, or "Nothing new worth preserving." if nothing qualified.

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. 1mo ago First seen · 41 lines · 32 tokens per session scan A 428e838a5e9f

Subscribe to this mod's changes

preserve is a skill published in the GitHub repository sliamh11/Deus (52 stars, last pushed today), licensed MIT. It adds 32 tokens to every session and 395 once invoked, about $0.0001 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 2026-09-03.

Claude CodeMemory and contextai-assistantai-memorypersistent memoryself-improving-aisemantic-memory
Related

Other skills, from other repositories

memcord

Privacy-first, self-hosted chat memory for OpenClaw — save and recall conversation history across sessions without any cloud dependency.

ukkit/memcord · 28 tokens

mem9

Persistent cloud memory for OpenClaw agents. Use when users say: "install mem9" "setup memory" "add memory plugin" "openclaw memory" "mem9 onboarding" "memory not working" "import memories" "upload sessions".

unvulcanised-watercress762/mem9 · 63 tokens

mem9

Persistent cloud memory for OpenClaw agents. Use when users say: "install mem9" "setup memory" "add memory plugin" "openclaw memory" "mem9 onboarding" "memory not working" "import memories" "upload sessions".

unvulcanised-watercress762/mem9 · 63 tokens

dynamic-resources

Example skill loaded from resourcesdiscover.

EXXETA/exxperts · 11 tokens

neuron-curated-memory

Use Neuron (the semantic-memory MCP server) the RIGHT way so its graph stays clean and useful. Before answering, load prior context; after answering, save a CURATED turn — 3-5 concept keywords (nouns/entities/tech, never verbs or filler), typed links with a short rationale, and never a self-link. This raises graph…

recla93/Neuron · 133 tokens

neuron-usage

Correct-usage playbook for the Neuron semantic memory MCP (neuron tools). Use when storing or recalling memories with Neuron, when deciding what to pass to preturn/storeturn, when the user says "remember this", "salva in memoria", "cosa ricordi di", "usa neuron", when curating keywords/links for the knowledge graph…

recla93/Neuron · 90 tokens