context-loader
/context-loader
Session start context priming -- loads relevant memories from Pensyve at the beginning of a session to provide continuity across sessions. Use when switching projects or needing historical context.
- Author
- major7apps ↗
- Repository
- pensyve ↗
- Licence
- Apache-2.0
- Last repository change
- 04.10.2026
Assessment and security
- Files in this package
- 1
- Scripts
- 0
- HTML comments
- 0
- URLs in SKILL.md
- 0
No signals detected. Repository changed on 04.10.2026, without references to retired models or APIs.
Apache-2.0, otwarta: można używać i zmieniać, z zachowaniem licencji i informacji o zmianach.
What it does and when to use it
Session start context priming -- loads relevant memories from Pensyve at the beginning of a session to provide continuity across sessions. Use when switching projects or needing historical context.
Original author description
Session start context priming -- loads relevant memories from Pensyve at the beginning of a session to provide continuity across sessions. Use when switching projects or needing historical context.
How it works
- Instructions
- Constraints
- Error Handling
SKILL.md preview
--- name: context-loader description: "Session start context priming -- loads relevant memories from Pensyve at the beginning of a session to provide continuity across sessions. Use when switching projects or needing historical context." version: 1.0.0 --- # Context Loader Load relevant memories from Pensyve at the start of a session to provide cross-session continuity. Respects the `context_loading` configuration setting. ## Instructions > **Note on invocation:** The SessionStart hook has already performed a scoped recall and (if applicable) injected a continuity primer. Invoking this skill adds deeper on-demand context — not a replacement for the hook's work. Expect to see both. When this skill is invoked (typically at session start), follow these steps: ### Step 0: Determine Loading Mode Check the `mode` argument if provided. Otherwise, respect the `context_loading` setting from the plugin configuration (`pensyve-plugin.local.md`): - **off**: Do nothing. Inform the user: "Context loading is disabled. Use `/recall` to search memories on demand." - **summary**: Load a concise overview (10-15 lines max). - **full**: Load comprehensive context with relevance scores and details. If no mode is specified and no configuration is found, default to **summary**. ### Step 1: Query Memories Run the following `pensyve_recall` queries to gather session context: 1. **Recent decisions**: `pensyve_recall` with query `"decided"` (limit: 5) 2. **Known issues**: `pensyve_recall` with query `"issue OR bug OR error OR problem"` (limit: 5) 3. **Workflow patterns**: `pensyve_recall` with query `"workflow OR pattern OR process"` (limit: 5) 4. **Recent activity**: `pensyve_recall` with query `"*"` (limit: 10) -- broad query to capture recent memories by recency Deduplicate results across queries (same memory ID should appear only once). ### Continuity-aware primer If the SessionStart hook detected a continuation (check plugin session state for `recent_context` — this is set by the hook when shared-entity score ≥0.7 against episodic recall results; it is a plugin-layer concept, not a structured server-side episode link), structure the primer around continuity rather than fresh recall: > **Continuing:** `<entity-set>` — prior work context > > **Last lessons:** > - [recent observation 1] > - [recent observation 2] > > **Open questions carried forward:** > - [if any observations had `open-question` provenance] **Note:** Continuity is best-effort — it is inferred from shared-entity overlap in recent episodic recall, not from a persisted episode-to-episode link. The MCP server has no episode-listing API today. When in doubt, the hook falls back to a fresh-session primer. If no continuation was detected, present a standard recall-based primer. ### Step 2: Present Context #### Summary Mode (10-15 lines max) Present a concise briefing with the most important items: > **Session Context** (from Pensyve memory) > > **Recent Decisions:** > > - auth-service: Using RS256 for JWT signing to support key rotation > - api-design: POST endpoints return 201 with created resource > > **Known Issues:** > > - database: Migration script requires Python 3.11+ > > **Active Patterns:** > > - testing: Integration tests need tmpdir cleanup after filesystem operations > > _Use `/recall <query>` to search for specific memories._ Rules for summary mode: - Maximum 15 lines of content (excluding the header) - Show at most 3 items per category - Omit categories with no results - Do not show scores, IDs, or timestamps - Prioritize higher-confidence and more recent memories #### Full Mode (comprehensive) Present a detailed briefing with scores and metadata: > **Session Context** (from Pensyve memory) > > **Recent Decisions** (3 found): > | Entity | Decision | Confidence | When | > |--------|----------|------------|------| > | auth-service | Using RS256 for JWT signing | 0.9 | 2026-03-15 | > | api-design | POST endpoints return 201 | 0.9 | 2026-03-14 | > | database | SQLite for MVP, migrate to Postgres later | 0.9 | 2026-03-12 | > > **Known Issues** (2 found): > | Entity | Issue | Confidence | Score | > |--------|-------|------------|-------| > | database | Migration requires Python 3.11+ | 0.8 | 0.91 | > | cache | Invalidation race condition on concurrent writes | 0.8 | 0.85 | > > **Workflow Patterns** (1 found): > | Entity | Pattern | Confidence | Score | > |--------|---------|------------|-------| > | testing | Integration tests need tmpdir cleanup | 0.7 | 0.78 | > > **Recent Activity** (5 unique memories, most recent first): > | Type | Entity | Summary | Score | > |------|--------|---------|-------| > | semantic | auth-service | RS256 JWT signing | 0.92 | > | episodic | database | Debugged migration failure | 0.88 | > | procedural | deploy | Run tests before deploy | 0.75 | > > _Total memories loaded: 11 | Use `/recall <query>` for targeted search | `/inspect <entity>` for entity details_ Rules for full mode: - Show all results with relevance scores - Include confidence values and timestamps where available - Group by category with counts - Show memory types in the recent activity section - Include a footer with total count and navigation suggestions ## Constraints - **Never read or write `.claude/` memory files.** All memory operations go through the Pensyve MCP tools exclusively. - Do not fabricate memories. Only display what the MCP tools return. - In summary mode, strictly respect the 15-line content limit. Truncate rather than exceed it. - Do not take any action based on the loaded context -- this skill is informational only. - If no memories are found at all, say: "No memories found in the current namespace. This appears to be a fresh session. Use `/remember` to start building context." - The context loading should be fast and non-blocking. Do not run expensive operations. ## Error Handling - If some `pensyve_recall` queries fail but others succeed, present the successful results and note the failures briefly. - If all queries fail, report the error and suggest checking the MCP server connection. - If the MCP server is not connected, inform the user: "Pensyve MCP server is not connected. Context loading skipped. Verify your MCP server configuration."
Versions
| Repository | Score | Licence |
|---|---|---|
| This page · major7apps/pensyve | 90 | Apache-2.0 |
| AkshatNaruka/aidentity | 100 | MIT |
| ibrahim-3d/orchestrator-supaconductor | 100 | AGPL-3.0 |
| tenxengineer/conductor_cc | 100 | MIT |
| thinkfleetai/memmesh | 95 | Apache-2.0 |
Database snapshot: 13.11.2026 · package version a67f55211880 (SHA-256 digest of the entire package)
Downloads in the last 30 days: 0 · ranking
Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.
Similar skills
- 90pensyve
Use when the user explicitly invokes Pensyve, asks what the agent remembers, wants Codex to recall or store project memory, requests memory health review, or wants memory grounded work. - 100mention-workflow
Use when the user types @pensyve, asks for an @-mention workflow, wants mention-style Pensyve memory access in Codex, or asks whether Pensyve supports Codex mentions. - 100agent-context-loader
Execute proactive auto-loading: automatically detects and loads agents.md files. Use when appropriate context detected. Trigger with relevant phrases based on skill purpose. - 100agent-context-loader
Execute proactive auto-loading: automatically detects and loads agents.md files. Use when appropriate context detected. Trigger with relevant phrases based on skill purpose. - 100mem0-context-loader
Search memories from earlier OpenCode sessions in this repository. Use it when earlier work may already explain the code, error, decision, or command you need, so you can avoid repeating file reads, searches, or experiments. - 100handoff
Create HANDOFF.md files for session continuity between conversations. Use when ending a session, switching context, or before /compact.