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 agentmods add skills/last9/mithai/memorynpx skills add last9/mithai --skill memorygit clone --depth 1 https://github.com/last9/mithaiWhat 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 | $0.00000 | $0.00176 |
| Opus 5 | $0.00000 | $0.00088 |
| Sonnet 5 | $0.00000 | $0.00035 |
| Haiku 4.5 | $0.00000 | $0.00018 |
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 2d 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
You have persistent memory across conversations. Your MEMORY.md is already loaded — check it before asking the user something you might already know.
You operate across multiple channels in the same organisation. Knowledge is shared and cumulative — what you learn in one channel applies everywhere. Treat MEMORY.md as the single source of truth for this org's tribal knowledge.
Before writing to MEMORY.md: read it first. Update or correct existing entries rather than appending duplicates. Use overwrite mode to keep the file clean and structured. Only add facts that are genuinely new or that correct something stale.
After learning something new (infrastructure facts, error patterns, team norms, corrections), save it with memory_write so you remember next time across all channels.
For multi-step procedures that worked, save them as playbooks in playbooks/ so you can reference them later.
What ships with it
1 file 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.
- 2d ago First seen · 20 lines · 0 tokens per session scan A 014378ea1de3
memory is a skill published in the GitHub repository last9/mithai (18 stars, last pushed 4d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 176 tokens. 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 2026-08-30.
Other skills, from other repositories
create-launch-post
Create and publish concise Rivet launch or changelog posts through an approval-gated workflow, including release research, a required user-selected hero variation, local HTML-rendered social and technical images, an R2 hero upload, MDX authoring, a reviewed draft GitHub PR for manual merge, and a scheduled and…
driver-test-runner
Methodically run the RivetKit driver test suite file by file across the native (NAPI) and wasm runtimes, tracking progress in /.agents/notes/driver-test-progress.md. Use when you need to validate the driver test suite after changes, bring up a new driver, or debug test failures systematically.
stack-merge
Bulk-merge a Graphite stack into main via admin-bypass fast-forward push. Replaces the Graphite merge queue for rivet-dev/rivet. Invoke when the user says "merge the stack at ", "ship everything through ", "bulk-merge up to ", "fast-forward main to ", or any request to land multiple stacked PRs at once in one shot.…
creating-docs-diagrams
Creates accessible hand-authored inline SVG architecture and sequence diagrams for documentation. Use when adding, replacing, or reviewing docs diagrams, especially Mermaid flowcharts.
openspec-bulk-archive-change
Archive multiple completed changes at once. Use when archiving several parallel changes.
openspec-ff-change
Fast-forward through OpenSpec artifact creation. Use when the user wants to quickly create all artifacts needed for implementation without stepping through each one individually.