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 instructions/villanub/borgmemory/agents-mdgit clone --depth 1 https://github.com/villanub/borgmemoryWhat 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 | $0.00942 | $0.00942 |
| Opus 5 | $0.00471 | $0.00471 |
| Sonnet 5 | $0.00188 | $0.00188 |
| Haiku 4.5 | $0.00094 | $0.00094 |
Grade A, and why
borgmemory AGENTS.md 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Project Borg
What is Borg?
Borg is a memory system connected via MCP. It maintains a knowledge graph of entities, facts, and procedures extracted from past conversations across all your AI tools. Use it to avoid re-explaining context and to make decisions informed by prior work.
When to use Borg
borg_think — Call BEFORE starting complex tasks
Call borg_think before any task that would benefit from knowing what was done previously. This compiles relevant context from the knowledge graph and returns it as structured output.
Always call borg_think when:
- Starting work on any file or module you haven't seen in this session
- Debugging an issue (retrieves past bugs, patterns, and related decisions)
- Making an architecture or design decision (retrieves prior decisions and rationale)
- Writing documentation, proposals, or RFPs (retrieves relevant facts and terminology)
- Asked about project history, prior decisions, or "what did we decide about X"
- Working in a namespace/project area you haven't touched recently
Example calls:
borg_think(query="APIM authentication issues", namespace="azure-msp", task_hint="debug")
borg_think(query="AMA compliance tracking architecture", namespace="azure-msp", task_hint="architecture")
borg_think(query="Project Sentinel customer targeting", namespace="azure-msp", task_hint="writing")
Task hints (use the most specific one):
debug— retrieves episodic memory + procedures + graph traversalarchitecture— retrieves semantic facts + graph neighborhoodcompliance— retrieves episode evidence + facts, excludes procedureswriting— retrieves semantic facts for accurate terminologychat— lightweight fact lookup (default)
borg_learn — Call AFTER significant events
Call borg_learn to record decisions, discoveries, and important context that should persist across sessions. The background worker extracts entities, facts, and procedures automatically.
Always call borg_learn when:
- A significant decision is made (technology choice, architecture change, policy)
- A non-obvious bug is diagnosed and fixed (root cause + solution)
- A new pattern or convention is established
- Important context is shared that would be lost when this session ends
- A meeting outcome, customer conversation, or requirement is discussed
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 · 96 lines · 942 tokens per session scan A 7f6647af4917
borgmemory AGENTS.md is an instructions file published in the GitHub repository villanub/borgmemory (2 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 942 tokens to every session, about $0.0047 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 instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.