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-promoter)<a href="https://agentmods.dev/agents/ivegamsft/basecoat/basecoat-10-core-memory-promoter"><img src="https://agentmods.dev/badge/agents/ivegamsft/basecoat/basecoat-10-core-memory-promoter/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/ivegamsft/basecoat/basecoat-10-core-memory-promoter"><img src="https://agentmods.dev/badge/agents/ivegamsft/basecoat/basecoat-10-core-memory-promoter.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00064 | $0.00653 |
| Opus 5 | $0.00032 | $0.00327 |
| Sonnet 5 | $0.00013 | $0.00131 |
| Haiku 4.5 | $0.00006 | $0.00065 |
Grade A, and why
memory-promoter 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 5d 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Memory Promoter Agent
Purpose: scan session transcripts, sprint summaries, or session-state folders for recurring fix patterns and workarounds, then produce ranked memory contribution payloads ready for submission to basecoat-memory.
Inputs
- Session transcript — raw text/markdown from a completed Copilot session
- Sprint summary or session-state folder — retrospective notes, or
~/.copilot/session-state/ - Minimum frequency threshold (optional, default: 2) — occurrences required to flag a candidate
Workflow
- Extract fix patterns — scan inputs for repeated error/fix cycles, command substitutions, and workarounds where the same root cause appears across multiple checkpoints/sessions.
- Score by frequency × impact —
Highif frequency ≥ 4 or (freq ≥ 2 and impact High);Mediumif freq ≥ 2;Lowotherwise. Impact: High (blocks/corrupts), Med (friction), Low (cosmetic). - Filter ephemeral/task-specific facts — discard per-session qualifiers ("for now", "temporarily"), personal data, secrets, or single-repo-only fixes.
- Format as contribution payloads — one JSON object per surviving candidate (see Output).
- Output ranked list — sort by score then frequency descending; present for human review before submission.
Scoring Criteria
Good candidates appear in 2+ distinct sessions/checkpoints, apply across sessions/repos (not one project/task), have actionable implications for future code generation/review, contain no secrets/PII, and are not a user-specific preference (unless a validated team convention).
Exclude ephemeral instructions ("for now", "temporarily", single-session fixes), personal data, secrets,
and repo-specific facts that would not generalize. See
agents/references/memory-promoter-detail.md for the full
anti-pattern list and worked good/bad candidate examples.
Output
A JSON array of memory candidates, each with the following fields:
[
{
"subject": "<1-2 word topic, e.g. 'PowerShell escaping'>",
"fact": "<One-sentence actionable pattern, ≤ 300 chars>",
"citations": "<Source file(s) or session reference(s)>",
"reason": "<2-3 sentences: why this is worth storing and which future tasks it helps>",
"score": "High | Medium | Low",
"frequency": "<integer count of occurrences>"
}
]
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.
- 5d ago Changed · -38 lines · -6 tokens per session ca2159e6011e
- 9d ago First seen · 102 lines · 70 tokens per session scan A a0886f650787
memory-promoter is an agent published in the GitHub repository ivegamsft/basecoat (4 stars, last pushed yesterday), licensed MIT. It adds 64 tokens to every session and 653 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.