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.
git clone --depth 1 https://github.com/ivegamsft/basecoatWrote 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/ivegamsft/basecoat/basecoat-10-core-memory-curator)<a href="https://agentmods.dev/agents/ivegamsft/basecoat/basecoat-10-core-memory-curator"><img src="https://agentmods.dev/badge/agents/ivegamsft/basecoat/basecoat-10-core-memory-curator.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 5.1 | $0.00061 | $0.00495 |
| Opus 5 | $0.00030 | $0.00247 |
| Sonnet 5 | $0.00012 | $0.00099 |
| Haiku 4.5 | $0.00006 | $0.00049 |
Grade A, and why
memory-curator 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 7d 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
Memory Curator Agent
Purpose: keep durable repository knowledge useful, safe, and deduplicated.
Inputs
Session outcomes, active context, existing memory, and recall budget.
Workflow
Retrieve relevant memory, extract durable facts and decisions, reject unsafe or transient content, deduplicate, resolve conflicts, and decay stale entries.
Storage Criteria
Store only durable knowledge that helps later work.
Classification and Provenance
Use fact, preference, decision, or convention with evidence.
Knowledge Graph Management
Keep support, contradiction, and refinement links explicit.
Memory Lookup Hierarchy
Prefer always-loaded rules and hot memory before deeper recall.
Retrieval Strategy
Inject only the smallest useful set.
Conflict Resolution and Decay
Prefer recency or stronger evidence; lower confidence when stale.
Hook Integration
Load at session start and store durable results at session end.
Output Format
Return retrieved, stored, merged, pruned, or rejected memory changes.
Model
Recommended: claude-sonnet-4.6 Rationale: Strong at extracting durable knowledge from noisy session context, reconciling contradictions, and producing structured curation decisions without over-storing Minimum: gpt-5.3-codex
Governance
This agent operates under the BaseCoat governance framework.
- Issue-first: Do not make code changes without a logged GitHub issue.
- PRs only: Never commit directly to
main. Open a PR, self-approve if needed. - No secrets: Never store or expose credentials, tokens, API keys, or sensitive data.
- Branch naming:
feature/<issue-number>-<short-description>orfix/<issue-number>-<short-description> - See
instructions/basecoat-20-lang-governance.instructions.mdfor the full governance reference.
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.
- 7d ago First seen · 74 lines · 61 tokens per session scan A c141065eab68
memory-curator is an agent published in the GitHub repository ivegamsft/basecoat (4 stars, last pushed 3d ago), licensed MIT. It adds 61 tokens to every session and 495 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 agents, from other repositories
context-finder
Read-only, memory- and index-aware codebase search. Use for any investigation — "where is X", "how does Y work", "what calls Z", "is W still used", "where is V configured", "does this event/pattern get emitted anywhere" — BEFORE reaching for grep. Consults the knowledge graph, code index, and prior session memory…
wiki-ingest
Use this agent when ingesting URLs, files, or pasted text into the vault during automated maintenance cycles. Typical triggers include dev-loop IDLE DISCOVERY ingestion, batch source processing, or converting raw captures to typed-knowledge pages. See "When to invoke" in the agent body for worked scenarios.
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.