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/binary16labs/prime-silo/memorynpx skills add binary16labs/prime-silo --skill memorygit clone --depth 1 https://github.com/binary16labs/prime-siloWhat 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 | $0.00015 | $0.00342 |
| Opus 5 | $0.00008 | $0.00171 |
| Sonnet 5 | $0.00003 | $0.00068 |
| Haiku 4.5 | $0.00002 | $0.00034 |
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.
This is a copy
100% identical to Memory — 2 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
Use prompt-include files as persistent memory.
paths
~/memory/behavior.system.include.md: stable behavior, user preferences, standing instructions, durable workflow rules~/memory/memories.transient.include.md: rolling notes worth keeping across conversations~/memory/*.transient.include.md: extra focused memory files when one topic deserves its own evolving note
rules
*.system.include.mdbecomes system-prompt instruction. Use it for slow-changing behavior.*.transient.include.mdbecomes transient context. Use it for notes, facts, project context, reminders, and other frequently updated memory.- if something meaningful should persist, create or update the right
~/memory/...include.mdfile instead of only acknowledging it in chat. - update memory frequently after meaningful progress, durable decisions, new user facts, or corrections that should shape later turns.
- when the user asks to change how you behave, edit
~/memory/behavior.system.include.md. - for small additive memory updates, prefer incremental file mutations such as
space.api.fileWrite({ path, content, operation: "append" })oroperation: "insert"over rereading and rewriting the whole memory file. Rewrite the full file only when you need cleanup, dedupe, or structural edits. - keep memory concise, specific, and current. Rewrite or delete stale lines instead of piling up duplicates.
- these files are plain markdown include bodies. Write the raw remembered content, not YAML frontmatter or wrapper commentary.
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 · 27 lines · 15 tokens per session scan A b43e81d4d908
Memory is a skill published in the GitHub repository binary16labs/prime-silo (5 stars, last pushed 9d ago), licensed MIT. It adds 15 tokens to every session and 342 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to Memory, differing in 2 lines, and is treated as a copy.
Other skills, from other repositories
draw-image
Generate an image from a text prompt using an OpenAI-compatible image generation API (gpt-image-1-mini or compatible). The image is uploaded to the gofile.io public file sharing service and ONLY the public download page URL is returned. Trigger when user asks to draw, paint, generate, or create an image.
compose:subagent
Use when executing implementation plans with independent tasks in the current session.
compose:merge
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup.
compose:plan
Use when you have a spec or requirements for a multi-step task, before touching code.
compose:report
Use after implementation is verified and before merge — consolidates multiple spec iterations into a single final-state report, marks related specs, and records key lessons.
compose:worktree
Use when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback.