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 agents/andrewbartels1/solidworksmcp-python/agent-memory-and-recoverygit clone --depth 1 https://github.com/andrewbartels1/SolidworksMCP-pythonWrote 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/agents/andrewbartels1/solidworksmcp-python/agent-memory-and-recovery)<a href="https://agentmods.dev/agents/andrewbartels1/solidworksmcp-python/agent-memory-and-recovery"><img src="https://agentmods.dev/badge/agents/andrewbartels1/solidworksmcp-python/agent-memory-and-recovery.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 | $0.00000 | $0.00307 |
| Opus 5 | $0.00000 | $0.00153 |
| Sonnet 5 | $0.00000 | $0.00061 |
| Haiku 4.5 | $0.00000 | $0.00031 |
Grade A, and why
agent-memory-and-recovery 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 4d 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.
What it actually says
Agent Memory and Recovery (SQLite MVP)
This documents a simple local SQLite strategy to help agents avoid repeated failures and recover from broken design states.
Goal
Capture enough execution history to answer:
- What failed?
- Where did it fail (tool + stage)?
- What is the likely root cause?
- What should we do next?
- Should we roll back before retrying?
Local Storage
Database path:
.solidworks_mcp/agent_memory.sqlite3
Core tables:
agent_runstool_eventserror_catalog
Error-Centric Recovery Loop
- Query
error_catalogfor similar failures bytool_name+error_type. - Present the top remediation options to the user.
- Prefer rollback/recovery actions before blind retries.
- Re-run with constrained parameters and capture outcome.
Example Troubleshooting Prompt
"Based on recent create_extrusion failures in the local SQLite catalog, suggest rollback-first recovery using existing MCP tools and avoid repeating known bad states."
Rollback-First Tooling Pattern
When a step fails:
- Capture snapshot metadata.
- Inspect recent feature-tree changes.
- Roll back/suppress latest risky feature.
- Re-run prerequisite validation tools.
- Retry only after preconditions pass.
Why This Helps
- Fewer repeated failures
- Faster root-cause diagnosis
- Better agent recommendations over time
- Better handoff between human and agent sessions
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.
- 4d ago First seen · 54 lines · 0 tokens per session scan A 97747e02e7d7
agent-memory-and-recovery is an agent published in the GitHub repository andrewbartels1/SolidworksMCP-python (68 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 307 tokens. 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 2026-08-30.
Other agents, from other repositories
performance-oracle
You are the Performance Oracle, an elite performance optimization expert specializing in identifying and resolving performance bottlenecks in software systems. Your deep expertise spans algorithmic complexity analysis, database optimization, memory management, caching strategies, and system scalability.
agentic-coding-performance-oracle
Analyzes code for performance bottlenecks, algorithmic complexity, database queries, memory usage, and scalability. Use after implementing features or when performance concerns arise.
mb-backend
Backend specialist for memory-bank /mb work stages. APIs, services, database, async/concurrency, server-side business logic. Falls back to mb-developer when stage is generic.
vector-db-cleanup
Removes stale chunks from the ChromaDB vector store for files that have been deleted or renamed on disk. Dry-run by default — shows what would be removed without deleting. Trigger when the user says "clean the vector database", "remove stale vector entries", "vector DB has orphaned chunks", or "sync the vector store…
silas
Database Architect. Use proactively for external knowledge imports (any "import / migrate / convert / bring in my [tool] notes"), SQLite mirror generation (SOP-002), frontmatter integrity audits, schema-drift triage across the eight PKM entity folders, and parsing failures. Owns WS-002.
mcp-summarizer
Context firewall for large MCP/grep/file payloads — returns concise summary to prevent context bloat. Dispatch before first MCP read-op (Linear/Sentry/Notion/Supabase/Figma/Slack/Langfuse/episodic-memory).