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 Mneno-AI/Mneno --skill mneno-memorygit clone --depth 1 https://github.com/Mneno-AI/MnenoWrote 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/mneno-ai/mneno/mneno-memory)<a href="https://agentmods.dev/skills/mneno-ai/mneno/mneno-memory"><img src="https://agentmods.dev/badge/skills/mneno-ai/mneno/mneno-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/mneno-ai/mneno/mneno-memory"><img src="https://agentmods.dev/badge/skills/mneno-ai/mneno/mneno-memory.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 | $0.00043 | $0.00314 |
| Opus 5 | $0.00022 | $0.00157 |
| Sonnet 5 | $0.00009 | $0.00063 |
| Haiku 4.5 | $0.00004 | $0.00031 |
Grade A, and why
mneno-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 10d 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
Mneno Memory
Use this skill when the repository has a .mneno/ workspace and the task may depend on prior project context.
Start of task
- Run
mneno status. - Run
mneno context "<current task>". - Verify important claims against repository files before acting.
During work
- Use
mneno search "<specific topic>"for narrow follow-up lookup. - Do not use Mneno for broad vague discovery.
- Do not assume Mneno is the source of truth.
Before stopping
Store one or more durable memories only if useful:
mneno add "..." --tag ...
Store:
- Decisions.
- Root causes.
- Constraints.
- Benchmark findings.
- Next steps.
Do not store:
- Secrets.
- Credentials.
- Huge logs.
- Routine edits.
- Generated code dumps.
References
Load only the reference needed for the current task:
- Read
references/AGENT_WORKFLOW.mdwhen the task is continuing prior work or the Mneno workflow is unclear. - Read
references/COMMAND_REFERENCE.mdbefore using unfamiliar CLI options or interpreting command output. - Read
references/MEMORY_GUIDELINES.mdbefore storing memories or choosing tags.
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.
- 10d ago First seen · 53 lines · 43 tokens per session scan A f8128c4319e9
mneno-memory is a skill published in the GitHub repository Mneno-AI/Mneno (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 43 tokens to every session and 314 once invoked, about $0.0002 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
aiception
Continuous learning system that extracts reusable knowledge from work sessions. Triggers: (1) /aiception command, (2) "save this as a skill" or "extract a skill", (3) "what did we learn?", (4) After non-obvious debugging or trial-and-error discovery. Creates new skills when valuable, reusable knowledge is identified.…
ob1-local-http
Capture and search thoughts against a self-hosted Open Brain over plain HTTPS, with no MCP transport involved. Use this skill in environments where Claude Code's MCP feature is disabled or the network blocks remote MCP endpoints, but the brain stack from the companion local-brain-no-mcp recipe is reachable on the…
deleting-thoughts
Use when asked to delete, remove, purge, wipe, or "get rid of" an Open Brain thought, or before calling deletethought (the open-brain-delete-thought connector), which HARD-deletes with no undo. Also use when tempted to delete a thought that is merely outdated or wrong. To edit or deprecate instead of removing, see…
live-retrieval
Automatically surfaces relevant Open Brain thoughts during active work. Fires on topic shifts (person names, project names, technologies mentioned). Silent on miss, brief on hit. The read side of the Open Brain flywheel. Use proactively when the user starts discussing a recognizable topic, mentions a person by name…
nbj-ob1-agent-memory-openclaw
Use Nate Jones OB1 Agent Memory from OpenClaw with provenance, scope, review, and use-policy discipline.
auto-capture
Automatically capture ACT NOW items and a session summary to Open Brain when a work session is ending. Use when wrapping a brainstorm, parking a project, finishing a Panning for Gold run, or otherwise closing a session with decisions worth remembering. Use the Open Brain capture tool available in the current client…