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/r007b34r/opencode-obsidian-knowledge-workflow/opencode-context-maintenancenpx skills add r007b34r/opencode-obsidian-knowledge-workflow --skill opencode-context-maintenancegit clone --depth 1 https://github.com/r007b34r/opencode-obsidian-knowledge-workflowWhat 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 | $0.00056 | $0.01176 |
| Opus 5 | $0.00028 | $0.00588 |
| Sonnet 5 | $0.00011 | $0.00235 |
| Haiku 4.5 | $0.00006 | $0.00118 |
Grade A, and why
opencode-context-maintenance 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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
opencode-context-maintenance
Constraints
- NEVER edit opencode.json, MCP config, model config, or git history automatically
- NEVER treat old wording as drift without evidence of conflict
- NEVER read the whole vault; find context entry points only
- NEVER default to config edits; defer config concerns to user
- Context is layered (3 layers); check all before recommending
Trigger Boundary
Use when: context is stale, records disagree with reality, configuration changed but notes did not, model/MCP assumptions drifted, OpenCode/Obsidian context should be checked.
Do NOT use for:
- Raw inbox sorting ->
inbox-triage - Week-level meaning extraction ->
weekly-synthesis - Direct vault CRUD ->
obsidian-mcpalone - Vault health diagnosis ->
vault-health-feedback - Promoting material ->
note-promotion
Boundaries
- Owns: context drift diagnosis, layer comparison, update recommendations
- Delegates to:
vault-health-feedback(drift reveals deeper vault health issue),obsidian-mcp(vault operations needed) - Never absorbs: inbox routing, synthesis, relationship analysis, promotion, direct config editing
Continuations
| Condition | Next skill |
|---|---|
| Drift reveals systemic vault health issue | vault-health-feedback |
| Context notes inaccessible, need vault operation | obsidian-mcp |
| Config changes needed that could break environment | Escalate to human |
Companion Skill
All vault operations follow obsidian-mcp. Forbidden: obsidian_patch_note, obsidian_append_to_note. Verify every write through readback.
Procedure
Phase 1: Identify Entry Points
obsidian_list_notes path:"Meta/"-> context source notes- Check OpenCode config state (read-only observation)
- Identify which layer is most likely drifted based on user report
Phase 2: Layer-Specific Diagnosis
When checking layers, read references/examples.md for drift calibration.
Long-term vault context (stable knowledge, methodology, project indexes):
- Read context source notes
- Compare claims against current vault state
- Flag outdated references, dead links, stale assumptions
What ships with it
6 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.
- 2d ago First seen · 137 lines · 56 tokens per session scan A eb77b0b3f619
opencode-context-maintenance is a skill published in the GitHub repository r007b34r/opencode-obsidian-knowledge-workflow (10 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 56 tokens to every session and 1,176 once invoked, about $0.0003 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
design-mcp-server
Design the tool surface, resources, and service layer for a new MCP server. Use when starting a new server, planning a major feature expansion, or when the user describes a domain/API they want to expose via MCP. Produces a design doc at docs/design.md that drives implementation.
add-tool
Scaffold a new MCP tool definition. Use when the user asks to add a tool, create a new tool, or implement a new capability for the server.
api-context
Canonical reference for the unified Context object passed to every tool and resource handler in @cyanheads/mcp-ts-core. Covers the full interface, its RequestContext base, all sub-APIs (ctx.log, ctx.state, ctx.requestInput, ctx.inputs, ctx.enrich, ctx.content), and when to use each.
api-linter
MCP definition linter rules reference. Use when bun run lint:mcp or bun run devcheck reports a lint error or warning (format-parity, schema-is-object, name-format, server-json-, etc.) and you need to understand the rule, its severity, and how to fix it. Every rule ID the linter emits has an entry in this doc.
api-canvas
DataCanvas primitive reference — a Tier 3 SQL/analytical workspace for tabular MCP servers, backed by DuckDB. Use when registering tables from upstream APIs, running ad-hoc SQL across them, and exporting results. Covers the acquire → register → query → export flow, per-table TTL, the token-sharing pattern for…
api-errors
McpError constructor, JsonRpcErrorCode reference, and error handling patterns for @cyanheads/mcp-ts-core. Use when looking up error codes, understanding where errors should be thrown vs. caught, or using ErrorHandler.tryCatch in services.