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/bikeread/promethos/design-agent-memorynpx skills add bikeread/promethos --skill design-agent-memorygit clone --depth 1 https://github.com/bikeread/promethosWrote 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/bikeread/promethos/design-agent-memory)<a href="https://agentmods.dev/skills/bikeread/promethos/design-agent-memory"><img src="https://agentmods.dev/badge/skills/bikeread/promethos/design-agent-memory.svg" alt="Measured on agentmods" 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 | $0.00021 | $0.00610 |
| Opus 5 | $0.00010 | $0.00305 |
| Sonnet 5 | $0.00004 | $0.00122 |
| Haiku 4.5 | $0.00002 | $0.00061 |
Grade A, and why
design-agent-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 6d 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Goal
Assign the right information to the right memory layer so recall is useful without becoming stale, noisy, or risky.
Inputs
- Types of information the agent may store
- Expected duration of usefulness
- Privacy, accuracy, and retrieval constraints
Non-Goals
- Solving all context problems through persistence
- Keeping every observation forever
Workflow
Trigger signals
- User says "它忘了" or "it keeps forgetting"
- Agent has no memory configuration but handles multi-session work
- Preferences are being re-stated every conversation
- Project facts and user preferences are starting to blur together
- Memory is growing without expiry rules
1. Classify the information by durability and ownership
Separate session state, project facts, user preferences, retrieved records, and ephemeral observations by how long they stay useful and who owns their truth. Be explicit about the difference between project truth (for example repository facts or policy) and user preferences so one does not silently overwrite the other. Success criteria: Each memory class has a distinct role and expected lifespan.
2. Define what earns a write
Specify what kinds of information should be written into each memory layer and what should be ignored, summarized, or left transient. Success criteria: The write policy is selective and intentional rather than "store anything that might matter."
3. Define read triggers and precedence
State when each memory layer should be consulted and which layer wins if stored facts disagree. Success criteria: Memory reads follow a stable precedence order instead of unpredictable mixing.
4. Define freshness, expiry, and override rules
Describe how memory becomes stale, how it is refreshed, and when human confirmation is required before acting on it. Success criteria: The design explicitly handles stale or conflicting memory.
5. Check trust and privacy boundaries
Review whether any memory class could accumulate misleading, sensitive, or over-personalized information. Success criteria: The strategy accounts for trust and privacy risk, not just recall utility.
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.
- 6d ago First seen · 81 lines · 21 tokens per session scan A a3a4a78643a3
design-agent-memory is a skill published in the GitHub repository bikeread/promethos (33 stars, last pushed 5mo ago), licensed MIT. It adds 21 tokens to every session and 610 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
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.