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 Bumblebiber/its-over-9k --skill memorygit clone --depth 1 https://github.com/Bumblebiber/its-over-9kWrote 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/bumblebiber/its-over-9k/memory)<a href="https://agentmods.dev/skills/bumblebiber/its-over-9k/memory"><img src="https://agentmods.dev/badge/skills/bumblebiber/its-over-9k/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/bumblebiber/its-over-9k/memory"><img src="https://agentmods.dev/badge/skills/bumblebiber/its-over-9k/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 | $0.00084 | $0.00728 |
| Opus 5.5 | $0.00034 | $0.00291 |
| Sonnet 5.5 | $0.00017 | $0.00146 |
| Haiku 4.5 | $0.00008 | $0.00073 |
Grade A, and why
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 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.
How it starts
The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
memory — Sessions Never Start From Zero
A memory MCP turns the most expensive part of every session — re-establishing context — into one cheap call. Supported backends:
- TIM (Theoretically Infinite Memory, https://github.com/Bumblebiber/tim) —
npm
tim-cli(bintim). Hooks use TIM when both backends exist; SessionStart usestim resolve-project. - hmem (https://github.com/Bumblebiber/hmem) — npm
hmem-mcp(binhmem). Stable alternative. Hooks fall back to hmem when TIM is absent.
Both follow the same token discipline below. Choose (or switch) via
/o9k-init. Custom MCPs can be wired manually; o9k-memory hooks only
auto-drive TIM and hmem.
No memory MCP configured? Point the user at /o9k-init (or
npm i -g tim-cli && tim init / npm i -g hmem-mcp && hmem init), then
continue without memory features.
Session start — briefing, not history
- Call the project-loading tool (
load_projector equivalent) ONCE. - Budget: the injected briefing must stay in the low hundreds of tokens — summaries and IDs, never full entries or raw history.
- Everything deeper is on-demand: drill into an entry only when the current task needs it (progressive disclosure — you pay for what you read).
During the session
- User references the past without an ID ("letzte Woche", "the schema we
chose", "that auth bug") → search memory BEFORE asking the user or grepping
the repo. Prefer dispatching the search (see
dispatch) so candidate entries never load into the main context. - Something durable happened — a decision with a reason, a lesson from a failure, an error and its fix, a milestone → write it now, compactly: one-line summary on top, detail below. Do not transcribe the conversation.
- Don't duplicate: search before writing; extend the existing entry instead of creating a twin.
Before context dies — the flush
Approaching compaction, /clear, or session end:
- Persist open state: what was done, what's in progress, the exact next step.
- Persist anything said-but-not-saved that survives the "will a future session need this?" test.
- THEN allow compaction/clear. Compaction summaries are lossy; memory is not.
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.
- 1mo ago First seen · 60 lines · 84 tokens per session scan A c4390c437c44
memory is a skill published in the GitHub repository Bumblebiber/its-over-9k (0 stars, last pushed 1mo ago), licensed MIT. It adds 84 tokens to every session and 728 once invoked, about $0.0003 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
mem0-oss-to-platform
Plan, then execute, a migration of a project from the mem0 open-source / self-hosted SDK (local Memory class) to the mem0 Platform / hosted SDK (MemoryClient). TRIGGER when: the developer wants to move, switch, or migrate mem0 off OSS/self-hosted to the hosted API, e.g. "migrate my mem0 setup to the platform", "switch…
forget
Remove a personal fact, preference, relationship detail, topic, or prior event from Muse's active memory and stop existing copies or automations from bringing it back. Use for explicit requests such as 'forget that', 'don't remember this about me', or 'remove that from your memory'. Do not use when 'forget it' merely…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
establishing-project-context
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.