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/codeinfinity1/stram/memory-metabolismnpx skills add CodeInfinity1/Stram --skill memory-metabolismgit clone --depth 1 https://github.com/CodeInfinity1/StramWhat 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 | $0.00042 | $0.00632 |
| Opus 5 | $0.00021 | $0.00316 |
| Sonnet 5 | $0.00008 | $0.00126 |
| Haiku 4.5 | $0.00004 | $0.00063 |
Grade A, and why
memory-metabolism 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.
How it starts
The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Memory Metabolism
Purpose
Keep durable memory useful over time. This skill adapts external reference active-maintenance and memory metabolism ideas into Stram's model-led memory curation path.
When To Use
Use when the user asks to clean memory, summarize past work, forget outdated details, preserve lessons, or review whether memory is helping current tasks.
Inputs And Evidence
memory_summaryfor recent or period-based history.memory_searchfor specific topics.cognitive_memory_curateproposals.- Current goals, commitments, persona, and skill records.
- User-stated preferences about remembering or forgetting.
Tool Map
memory_summarymemory_searchmemory_writememory_profilecognitive_memory_curatecognitive_curation_statuscognitive_state
Workflow
- Define the curation purpose: retain, summarize, archive, forget, deduplicate, or audit.
- Gather current memory records relevant to that purpose.
- Use model-led curation for semantic decisions about value and staleness.
- Preserve exact evidence references for memories that remain.
- Archive or forget only when evidence is obsolete, unsupported, user-requested, or superseded.
- Report what changed and what was intentionally left untouched.
Safety And Boundaries
- Never delete or alter memory solely because it is inconvenient.
- Respect explicit user forget requests while preserving audit requirements.
- Do not infer sensitive stable facts from weak evidence.
Safety And Approval
- Treat memory writes, curation, archiving, and forgetting as durable state changes.
- Keep explicit user forget requests high priority, while preserving any required audit trace.
- Do not promote sensitive, protected, medical, legal, financial, or identity-related facts unless clearly useful and evidence-supported.
- Do not let memory cleanup remove active commitments, unresolved blockers, or live-task context.
Native Implementation Boundaries
- Use Stram memory summary/search/write/profile and cognitive memory curation tools.
- external reference memory-metabolism ideas are reference patterns; retention, summarization, and forgetting decisions must be model-led through native curation.
- Deterministic code validates records and stores evidence, but must not infer semantic staleness or user preferences without the model or explicit user instruction.
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 · 79 lines · 42 tokens per session scan A 6b644bef57bf
memory-metabolism is a skill published in the GitHub repository CodeInfinity1/Stram (10 stars, last pushed 22d ago), licensed MIT. It adds 42 tokens to every session and 632 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
skills-installer
Install, list enabled, validate, or package LiveAgent skills. Use when you need to inspect the skills enabled in the current conversation, import a local skill directory or package, search/install from ClawHub, install from a GitHub repo/tree URL, or reconcile conflicts during an upgrade.
omh-jit-learn
This is a Hermes-native jit-learn workflow skill.
omh-instinct-ledger
This is a Hermes-native instinct-ledger workflow skill.
case-study
Craft a portfolio case study with narrative arc, process evidence, and outcomes. Use when telling a project's story to an external audience. For an internal stakeholder deck, use presentation-deck.
xiaohongshu-title
《小红书运营手册 · AI工作台》标题生成与优化技能。用于用户明确要为小红书笔记、封面短句、图文/短视频标题、种草、教程、测评、服务内容起标题、改标题、做标题方向选择时触发。输入可以是正文草稿、选题方向、产品卖点、账号定位、图片/视频描述或已有标题。默认用快速模式输出标题；用户要求分析、首推、理由、方向、诊断或优化时用诊断/优化模式。不要在普通文章标题、论文标题、新闻标题、课程命名等非小红书/社媒场景中自动触发。.
mulch-record-from-evidence
Turn the evidence of a finished work session — git commits, changed files, recently-touched seeds issues — into well-formed ml record invocations. Use at session close, when an agent has made changes worth preserving as mulch expertise but hasn't yet recorded them.