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/the-metafactory/soma/memorynpx skills add the-metafactory/soma --skill memorygit clone --depth 1 https://github.com/the-metafactory/somaWrote 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/the-metafactory/soma/memory)<a href="https://agentmods.dev/skills/the-metafactory/soma/memory"><img src="https://agentmods.dev/badge/skills/the-metafactory/soma/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 | $0.00085 | $0.01033 |
| Opus 5 | $0.00043 | $0.00517 |
| Sonnet 5 | $0.00017 | $0.00207 |
| Haiku 4.5 | $0.00009 | $0.00103 |
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 3d 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Memory
Soma memory is a files-first store of markdown notes under the memory/ tree.
Every note carries frontmatter (id, type, created, last_verified, provenance,
trust, source_of_truth, links, resurface_count). There is NO model in the loop:
each operation is a deterministic soma memory CLI subcommand. This skill routes
a memory request to the right subcommand and reads back its result — it never
edits note files by hand.
Note model (what lives where)
| Type | Dir | What it holds | Trust |
|---|---|---|---|
| semantic | memory/semantic/ |
durable facts | principal or assistant |
| procedural | memory/procedural/ |
durable how-to / SOPs | principal or assistant |
| episodic | memory/episodic/sessions,actions/ |
session digests + planned-action logs | assistant |
| (generated) | memory/INDEX.md |
the earned-inclusion index over durable notes | — |
| (archive) | memory/archive/ |
pruned episodic notes + monthly digests | — |
Trust is DERIVED from how a note was written, never set by a flag. A
principal-correction write needs --principal-authority; import writes are
lower trust. Episodic notes (session digests, action logs) are written at
assistant trust by the assistant itself. Consolidation NEVER mints or elevates
trust — it only ages or relocates existing notes.
Fast Path
- Identify the requested operation from the routing table.
- Load ONLY that workflow file from
Workflows/. - Run the single
soma memorycommand it specifies; report its output verbatim. - Never hand-edit files under
memory/— the CLI owns the schema, INDEX, and event log. A hand edit can desync the INDEX; the audit flags a note NEWER than INDEX by mtime, but a mtime-preserving edit slips past — always runsoma memory reindexafter any manual change.
Routing
| Intent | Workflow | Command |
|---|---|---|
| Save a durable fact / SOP | Workflows/Remember.md |
soma memory write … |
| Retrieve what is known about X | Workflows/Recall.md |
soma memory recall <query> |
| Log a session digest or a planned action | Workflows/Remember.md |
soma memory digest / soma memory action |
| Run maintenance (prune, digest, stale-mark, dedup) | Workflows/Consolidate.md |
soma memory consolidate |
| Check memory-tree health | Workflows/Audit.md |
soma memory audit |
What ships with it
4 files 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.
- 3d ago First seen · 76 lines · 85 tokens per session scan A 59c65d30672c
Memory is a skill published in the GitHub repository the-metafactory/soma (8 stars, last pushed 5d ago), licensed MIT. It adds 85 tokens to every session and 1,033 once invoked, about $0.0004 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…