scos-memory
Use the SCOS Memory Fabric's mcp-gateway tools (scos_recall, scos_status, scos_explain, scos_user_model, scos_memory_graph, scos_correct, scos_forget…
Skill by dylmarriner
Chalk Labs
Need help deploying scos-memory?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/dylmarriner-scos-memory-69f5f2
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/scos-memory
What's inside
- Skill name
scos-memory- Description
- Use the SCOS Memory Fabric's mcp-gateway tools (scos_recall, scos_status, scos_explain, scos_user_model, scos_memory_graph, scos_correct, scos_forget, scos_graphify_query, scos_graphify_path, scos_graphify_explain) to search, inspect, and manage persistent cross-session memory, including the graphify codebase knowledge graph. Use when the user says "recall", "what do you remember about", "check memory status", "why do you believe/remember", "forget that", "that's wrong, it's actually", or asks how parts of the codebase connect.
- License
- MIT
- Instructions
- 89 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
This plugin has two mechanisms working together, and they cover different gaps: - **`hooks/hooks.json`** fires a `SessionStart` reminder automatically, every session, with no action from you — it's already told you to call `scos_recall` before answering from assumption. Don't re-derive that instruction from this skill; it's already in context by the time you read this file. - **This skill** is what fills in the rest: the four read-only inspection tools the hook doesn't detail, and the two mutating ones that need care. It also covers the three slash commands (`/scos-recall`, `/scos-explain`, `/scos-status`) — those exist for when the *user* wants to trigger a lookup directly rather than you inferring the need for one. ## Tools | Tool | Purpose | Required args | |---|---|---| | `scos_recall` | Search memory for relevant context | `query` (string), `max_items` (optional int) | | `scos_status` | Check memory provider health/reachability | none | | `scos_explain` | Show why a memory is held and its supporting evidence | `memory_id` | | `scos_user_model` | Inspect the stored user representation | none | | `scos_memory_graph` | Inspect memory entities and their relationships | none | | `scos_correct` | Correct a stored memory, preserving the superseded version | `memory_id`, `value` | | `scos_forget` | Request removal of a specific memory | `memory_id` | | `scos_graphify_query` | Ask a plain-language question against the graphify codebase knowledge graph | `q` | | `scos_graphify_path` | Trace the shortest path between two concepts in the graph | `from`, `to` | | `scos_graphify_explain` | Explain one node in the graph and list its connections | `node` | ## When to use each - **The hook already nudged you at session start** — but recall again mid-session too, whenever the topic shifts to something the opening recall wouldn't have covered. One recall at session start doesn't cover a whole session. - **User runs `/scos-recall [query]`** → that's an explicit, user-triggered lookup; present only what the tool returns, same as any other call. - **User asks whether memory/the connection is working** → `scos_status`, or `/scos-status`. - **User asks "why do you think/remember that" about a specific fact** → `scos_explain` with that memory's id (get the id from a prior `scos_recall` result, don't invent one), or `/scos-explain [memory_id]`. - **User asks what you know about them, broadly** → `scos_user_model`. - **User asks how memories relate to each other, or wants a broader picture** → `scos_memory_graph`. - **User says a stored fact is wrong** → `scos_correct`, quoting back the corrected value before calling, since it's a mutation. - **User explicitly asks to forget/delete something** → `scos_forget`, only after confirming the specific `memory_id` and getting the user's explicit go-ahead — this is destructive and not easily undone. - **User asks how two things in the codebase connect, or wants a scoped answer instead of grepping** → `scos_graphify_query` for an open question, `scos_graphify_path` for two named things, `scos_graphify_explain` for one node's connections. ## Caution: `scos_correct` and `scos_forget` As of the current `mcp-gateway` build, these two tools are wired into the tool list but have **no backing implementation** on this fleet (`services/mcp-gateway/cmd/server/main.go` routes them to a stub). Calling them may return an error or a no-op rather than actually mutating memory. Tell the user this if a call doesn't behave as expected — don't assume silence means success. ## Anti-patterns WRONG: skipping `scos_recall` after the session-start hook fires, on the theory that the hook already "did the recall." The hook is a reminder, not a substitute for calling the tool with a query relevant to the current question. RIGHT: call `scos_recall` yourself, with a query specific to what's being asked, and only report "nothing found" after the tool actually returns empty. WRONG: calling `scos_forget` because the user seems annoyed about something being remembered, without asking which specific memory. RIGHT: ask for (or look up via `scos_recall`/`scos_memory_graph`) the exact `memory_id`, restate what will be forgotten, and get confirmation first. ## See also - `docs/agent-connection-guide.md` — how the gateway is wired for every agent on this fleet, and where credentials live. - `integrations/claude/README.md` — how this plugin and the Desktop extension both point at the same backend.
From dylmarriner/scos-memory, MIT.
More from dylmarriner/scos-memory
- 0.529score
tunnel-mcp
dylmarriner
Create, connect, list, and inspect MCP tunnel runtimes through the local tunnel-client plugin.
SkillBFreshness: BClaude Code +9 - 0.524score
scos-memory
dylmarriner
Use the SCOS Memory Fabric's mcp-gateway tools (scos_recall, scos_status, scos_explain, scos_user_model, scos_memory_graph, scos_correct, scos_forget) to…
SkillBFreshness: BClaude Code +9 - 0.521score
hostile-data-flow-auditor
dylmarriner
Trace attacker-influenced data through parsing, normalization, validation, storage/reload, transformation, serialization, caches, templates, filesystem…
SkillBFreshness: BClaude Code +9 - 0.521score
hostile-authentication-identity-auditor
dylmarriner
Audit identity lifecycle, sessions, cookies, tokens, verification, refresh, revocation, MFA, recovery, impersonation, linking, OAuth/OIDC, API keys, service…
SkillBFreshness: BClaude Code +9 - 0.521score
hostile-authorization-auditor
dylmarriner
Map every sensitive operation to every reachable interface and verify ownership, roles, object/function auth, tenant isolation, admin, service, worker, and…
SkillBFreshness: BClaude Code +9 - 0.521score
hostile-blind-spot-auditor
dylmarriner
Run last and explicitly try to prove the other auditors missed something, prioritizing clean, internal-only, operational, configuration-only, well-tested, and…
SkillBFreshness: BClaude Code +9 - 0.521score
hostile-business-logic-abuse-auditor
dylmarriner
Attack product invariants using legitimate functionality: sequence abuse, replay, duplicates, quotas, entitlements, approvals, ownership, lifecycle…
SkillBFreshness: BClaude Code +9 - 0.521score
hostile-concurrency-auditor
dylmarriner
Find races, TOCTOU, stale reads, locking gaps, optimistic concurrency failures, duplicate jobs/events, retries, ordering, idempotency, cancellation races, and…
SkillBFreshness: BClaude Code +9 - 0.521score
hostile-configuration-auditor
dylmarriner
Audit environment variables, defaults, flags, permissions, dev/prod differences, debug, deployment, containers, infrastructure, unsafe combinations, and…
SkillBFreshness: BClaude Code +9 - 0.521score
hostile-control-flow-auditor
dylmarriner
Trace sensitive operations from every reachable entry through callers, callees, callbacks, middleware, RPC, events, workers, queues, persistence, external…
SkillBFreshness: BClaude Code +9 - 0.520score
scos-memory
dylmarriner
Use the SCOS Memory Fabric tools (scos_recall, scos_status, scos_explain, scos_user_model, scos_memory_graph, scos_correct, scos_forget, scos_graphify_query…
SkillBFreshness: BClaude Code +9 - 0.513score
scos-memory
dylmarriner
Use SCOS Memory Fabric for prior context and governed memory operations.
SkillBFreshness: BClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Aug 22, 2026 (2 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/dylmarriner/scos-memory
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from dylmarriner
- 0.529score
tunnel-mcp
dylmarriner
Create, connect, list, and inspect MCP tunnel runtimes through the local tunnel-client plugin.
SkillBFreshness: BClaude Code +9 - 0.524score
scos-memory
dylmarriner
Use the SCOS Memory Fabric's mcp-gateway tools (scos_recall, scos_status, scos_explain, scos_user_model, scos_memory_graph, scos_correct, scos_forget) to…
SkillBFreshness: BClaude Code +9 - 0.521score
hostile-authorization-auditor
dylmarriner
Map every sensitive operation to every reachable interface and verify ownership, roles, object/function auth, tenant isolation, admin, service, worker, and…
SkillBFreshness: BClaude Code +9 - 0.521score
hostile-authentication-identity-auditor
dylmarriner
Audit identity lifecycle, sessions, cookies, tokens, verification, refresh, revocation, MFA, recovery, impersonation, linking, OAuth/OIDC, API keys, service…
SkillBFreshness: BClaude Code +9 - 0.521score
hostile-blind-spot-auditor
dylmarriner
Run last and explicitly try to prove the other auditors missed something, prioritizing clean, internal-only, operational, configuration-only, well-tested, and…
SkillBFreshness: BClaude Code +9 - 0.521score
hostile-business-logic-abuse-auditor
dylmarriner
Attack product invariants using legitimate functionality: sequence abuse, replay, duplicates, quotas, entitlements, approvals, ownership, lifecycle…
SkillBFreshness: BClaude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get scos-memory running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
scos-memory skill. Agent Mart. https://agentmart.dev/skills/dylmarriner-scos-memory-69f5f2 (last updated 2026-10-24)