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 cbuntingde/kimi-memory --skill list_memoriesgit clone --depth 1 https://github.com/cbuntingde/kimi-memoryWrote 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/cbuntingde/kimi-memory/list_memories)<a href="https://agentmods.dev/skills/cbuntingde/kimi-memory/list_memories"><img src="https://agentmods.dev/badge/skills/cbuntingde/kimi-memory/list_memories.svg" alt="Measured on agentmods" 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 | $0.00050 | $0.00287 |
| Opus 5 | $0.00025 | $0.00143 |
| Sonnet 5 | $0.00010 | $0.00057 |
| Haiku 4.5 | $0.00005 | $0.00029 |
Grade A, and why
list_memories 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 7d 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.
What it actually says
list_memories
Show the durable memory entries currently on file.
By default this calls memory_list with scope: "all", so both the active project's durable memory and the cross-project global layer are returned. Each entry is annotated with the scope it came from (scope: "project" or scope: "global").
If the user explicitly asks for one scope, pass it through:
- "list memories for this project" →
scope: "project". - "list global memories" / "list cross-project memories" →
scope: "global". - "list memories" (unqualified) →
scope: "all".
Natural-language triggers include:
- "list memories"
- "show project memory"
- "what do you remember about this project"
- "list global preferences"
- "list_memories"
Always pass the project root (the cwd of the current session) as cwd. The server never infers it.
When the user asks for a topic, also call memory_recall with the same scope (default all) to surface keyword hits beyond plain listing.
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.
- 7d ago First seen · 29 lines · 50 tokens per session scan A d6004183c4d9
list_memories is a skill published in the GitHub repository cbuntingde/kimi-memory (0 stars, last pushed 3d ago), licensed MIT. It adds 50 tokens to every session and 287 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 2026-08-31.
Other skills, from other repositories
membrain
Shared long-term memory over MCP. Call memorycontext once at the start of any session/task to load what is already known; use searchmemory before answering questions about the user or their projects; save durable facts, preferences, and decisions with savememory / savememories. All agents and the user share the same…
delx-memory
Local-first agent memory MCP. No API keys. Prefer MCP tools if connected; otherwise the package CLI. Use when the user wants Delx Memory data or actions through an agent.
memorix-memory
Use when prior workspace context, past decisions, solved bugs, handoff state, or durable project knowledge would help a coding task.
plur-memory
Persistent learning for AI agents. Open engram format. Your agent learns from corrections, remembers across sessions, and transfers knowledge across domains.
memorix
Use when Claude Code needs Memorix shared memory, reasoning, Git Memory, mini-skills, session handoff, orchestration coordination, or integration troubleshooting.
plur-session-end
Extract durable learnings at the end of a session. Saves corrections, preferences, and codebase patterns as engrams — nothing ephemeral, nothing sensitive.