Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/Cloto-dev/CPersonanpx agentmods add skills/cloto-dev/cpersona/cpersona-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/cloto-dev/cpersona/cpersona-memory)<a href="https://agentmods.dev/skills/cloto-dev/cpersona/cpersona-memory"><img src="https://agentmods.dev/badge/skills/cloto-dev/cpersona/cpersona-memory/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/cloto-dev/cpersona/cpersona-memory"><img src="https://agentmods.dev/badge/skills/cloto-dev/cpersona/cpersona-memory.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 5 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 213 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium MCP Rug Pull · line 73 uvx/uv tool run commands without ==version create a rug-pull risk.Fix: Pin the version: uvx package-name==1.2.3
- medium Rogue Agent · line 155 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Memory Poisoning · line 187 Skill injects content designed to persist in agent memory or context across interactions. Persistent injection can alter agent behavior long after the initial interaction.Fix: Do not allow untrusted input to persist in agent memory or context. Validate all content before storing and implement memory isolation between sessions.
- medium Memory Poisoning · line 239 Skill injects content designed to persist in agent memory or context across interactions. Persistent injection can alter agent behavior long after the initial interaction.Fix: Do not allow untrusted input to persist in agent memory or context. Validate all content before storing and implement memory isolation between sessions.
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 | $0.00151 | $0.08432 |
| Opus 5.5 | $0.00060 | $0.03373 |
| Sonnet 5.5 | $0.00030 | $0.01686 |
| Haiku 4.5 | $0.00015 | $0.00843 |
Grade A, and why
cpersona-memory 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 yesterday.
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.
How it starts
The opening of the file, as written. The whole thing — 577 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CPersona — persistent memory for Claude
CPersona is an MCP server that gives Claude
persistent memory across sessions. It stores memories in a single local SQLite
file and retrieves them with a 3-layer hybrid search (vector + FTS5 + keyword,
merged by Reciprocal Rank Fusion). It has zero LLM dependency — the server
never calls a model, so memory adds no generative API cost and stays out of
your token budget; the calling agent (you) does all summarization. (Embedding
is separate: EMBEDDING_MODE=api bills per store and per recall against
CPERSONA_EMBEDDING_API_URL. The local http mode and none cost nothing.)
- Single SQLite file, MIT licensed.
- Works with Claude Code, Claude Desktop, Codex CLI, Cursor, VS Code, and any other MCP host.
- Repo: https://github.com/Cloto-dev/cpersona
This skill has two jobs: (1) help the user install and configure CPersona, and (2) use it correctly once it is connected.
When to use this skill
Activate this skill when any of the following is true:
- The user asks Claude to remember something across sessions, or complains that Claude forgets context between conversations.
- The user asks to install / set up / configure CPersona or "a memory server".
- CPersona MCP tools (
store,recall,archive_episode, …) are connected and the current turn contains a decision, a standing rule/preference, a bug finding, or a session boundary (start/end). - A
recallresponse carries anadvisoryfield, astoreresponse comes backembedded: false, or the user reports that memory search has got worse.
If CPersona tools are not connected and the user wants memory, go to Setup. If they are connected, go to Usage — or to When recall is degraded if a signal in the last bullet is what brought you here.
Setup
CPersona is a Python MCP server. Installing it has two parts: the memory server and a strongly recommended embedding server (it powers the vector-search layer). Running without an embedding backend is supported as a fallback — CPersona then serves FTS5 + keyword only — but it is not recommended for normal operation.
What ships with it
2 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.
- yesterday Changed · +1 lines 2817743025a9
- 3d ago Changed c791fabd8860
- 4d ago Changed · +4 lines 8bed7b06a84c
- 5d ago Changed · +3 lines 774134fc2f95
- 11d ago Changed · +10 lines c0204a18d729
- 12d ago Changed b94fb8358b44
- 19d ago Changed 62b02303c0b7
- 20d ago Changed · +1 lines 297df41d0247
- 22d ago Changed b992683dbdae
- 24d ago First seen · 558 lines · 151 tokens per session scan A 5103be092d46
cpersona-memory is a skill published in the GitHub repository Cloto-dev/CPersona (9 stars, last pushed today), licensed MIT. It adds 151 tokens to every session and 8,432 once invoked, about $0.0006 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.
Other skills, from other repositories
using-cortex-memory
Use when connected to a Cortex memory MCP server (tools named memorize, recall, recallabout, recalltimeline, listmemories, forget) — at session start, before asking the user for facts they may have shared before, after learning durable facts/preferences/decisions, when the user says "remember/recall/forget", or when…
mnema
Use the Mnema MCP server to give the AI long-term, searchable memory. Use it whenever the user shares durable facts, preferences, decisions, or context worth recalling in future sessions. Mnema stores memories in a vector database and recalls them with semantic + hybrid search, with decay scoring and summarization so…
graphmind-memory
A skill connects an agent to GraphMind, a shared memory system for retaining project knowledge across sessions and people. It restores context, records work and decisions, and consolidates the session afterward.
using-axon
Use when operating an installed Axon through its MCP tool or CLI to search, index sources, query the corpus, extract data, manage jobs or watches, and troubleshoot the RAG stack. For first-time setup or deployment repair, use install-axon.
pensieve
The user's personal Pensieve memory — a persistent, self-organising knowledge base that survives across sessions. Use whenever the user mentions "pensieve", asks about "my streams" / "my memory" / "what have I saved", says "add this to pensieve" / "remember this" / "save this", asks "what do I know about ", or wants…
add-mwe-memory
Give this NanoClaw's agents persistent, governed memory from an mwe-mcp server. Every turn is remembered and recalled mechanically, per speaker, with the built-in memory tree switched off and no session carried between turns.