agentmods.dev

memory-write

memory-write is a skill for Claude Code from LH8PPL/core-memory-kit. It costs 202 tokens per session (1,350 once invoked), scanned A, original, MIT.

A skill that saves durable project facts through Core Memory Kit's protected write process. It checks for secrets, duplicate facts, conflicting information, and unsafe local paths before saving.

In plain words
What is it for?
It is for recording, updating, or removing durable project memories when the user asks the agent to remember or forget something.
Why use it?
It lets the agent remember useful decisions and preferences without directly editing the memory files in ways that could leak sensitive information.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the core-memory-kit plugin — 4 skills, 8 hooks shipped together

not rated 7repo 15d ago A scan SkillSpector: pass 202 tokens original MIT

Good fit It is for recording, updating, or removing durable project memories when the user asks the agent to remember or forget something.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/lh8ppl/core-memory-kit/memory-write
View source ↗ LH8PPL/core-memory-kit
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 LH8PPL/core-memory-kit --skill memory-write
Clone the repo
git clone --depth 1 https://github.com/LH8PPL/core-memory-kit

Made for: Claude Code.

Or install core-memory-kit, the plugin that ships this one along with the rest of its 4 skills, 8 hooks.

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 memory-write

README.md
[![agentmods](https://agentmods.dev/badge/skills/lh8ppl/core-memory-kit/memory-write/github.svg)](https://agentmods.dev/skills/lh8ppl/core-memory-kit/memory-write)
Your own site
<a href="https://agentmods.dev/skills/lh8ppl/core-memory-kit/memory-write"><img src="https://agentmods.dev/badge/skills/lh8ppl/core-memory-kit/memory-write/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 memory-write

Your own site · 80×15
<a href="https://agentmods.dev/skills/lh8ppl/core-memory-kit/memory-write"><img src="https://agentmods.dev/badge/skills/lh8ppl/core-memory-kit/memory-write.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 202 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,350 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 $0.00202 $0.01350
Opus 5.5 $0.00081 $0.00540
Sonnet 5.5 $0.00040 $0.00270
Haiku 4.5 $0.00020 $0.00135

Measured 1mo ago against content hash 6374a26c2830, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

memory-write 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.

plugin/skills/memory-write/SKILL.md · 130 lines

How it starts

The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Capturing durable memory

Durable facts — preferences, decisions, environment state — are saved through the kit's safe write path (Poison_Guard secret screening + home-path sanitization + dedup + conflict detection).

  • NEVER hand-edit context/MEMORY.md, context/USER.md, or any file under context/memory/. Direct edits bypass screening and can leak a credential or a local path into a committed file.
  • Silent on success. Do not announce "saved to memory" unless the user asked.

There are two equivalent surfaces onto the same safe path. Prefer the MCP tools when the cmk server is connected — params are structured data, so backtick / $() / quote-heavy rationale can't be mangled by a shell, and there's no per-command approval prompt.

Preferred: the cmk MCP tools (when connected)

  • Capture → call mk_remember with text. For a preference, working-style rule, or constraint, also pass why, how, title, and type — this writes a rich Why/How fact file, not just a bullet.
  • Remove → call mk_forget with the fact id. Two-step: the first call previews what would be removed and returns a confirm_token; call again with that token to tombstone (audit trail preserved). Confirm with the user first.
  • Adjust trust → call mk_trust with the fact id and a level of low, medium, or high. Use when the user signals how much a saved fact matters: "trust this" / "that's important — keep it" → high; "that's not important / I'm not sure / low priority" → low. Trust drives what gets injected first and what ages out, so this is the user steering their own memory without editing files.

type is one of:

  • feedback — how the user wants you to work
  • user — who the user is (role, expertise)
  • project — an ongoing goal or constraint
  • reference — a pointer to an external resource (URL, ticket, dashboard)

Fallback: the cmk CLI (when the MCP server isn't connected)

Capture a bullet:

cmk remember "<the fact, one sentence>"

Read the full file on GitHub · 130 lines

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 · 130 lines · 202 tokens per session scan A 6374a26c2830

Subscribe to this mod's changes

memory-write is a skill published in the GitHub repository LH8PPL/core-memory-kit (7 stars, last pushed 15d ago), licensed MIT. It adds 202 tokens to every session and 1,350 once invoked, about $0.0008 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 2026-08-31.

Claude CodeMemory and contextagent-memoryai-agentsai-memoryanthropicclaude
Related

Other skills, from other repositories

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

ultramemory-snapshot

Compose and save a durable, wayback-grade session snapshot to UltraMemory. Use this whenever you are asked to write a session snapshot or rollup of the work just done — in particular when the UltraMemory capture hook nudges you to "Compose a session snapshot per the ultramemory-snapshot Skill rubric ... and save it…

LogicLabsAI/ultramemory-mcp · 97 tokens

setup

Guides Claude through first-time UltraMemory configuration after plugin install — API key, MCP server registration, test recall, and 401/403 troubleshooting.

LogicLabsAI/ultramemory-mcp · 32 tokens

save-topic

Use when the user wants to save or checkpoint topic progress, persist current discussion state, or save all topics before ending a session.

hatawong/claude-recap · 29 tokens

ignore-topic

Use when the user wants to ignore, skip, or exclude specific topics from being archived. Triggers on "ignore topic", "don't archive", "skip topic", "stop remembering", "list ignored topics", "remove ignore rule".

hatawong/claude-recap · 50 tokens