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/goncalompontes/mind-forge/agents-mdgit clone --depth 1 https://github.com/goncalompontes/mind-forgeWhat 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 | $0.01247 | $0.01247 |
| Opus 5 | $0.00624 | $0.00624 |
| Sonnet 5 | $0.00249 | $0.00249 |
| Haiku 4.5 | $0.00125 | $0.00125 |
Grade A, and why
mind-forge 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mind Forge — Architecture Decisions
Plugin: OpenCode plugin for document-based knowledge management
Status: MVP implemented
Date: 2026-06-28
Design Decisions (from Phase 4 Discussion)
D-01: Architecture — OpenCode plugin (separate from FlowDeck).
- Rationale: FlowDeck is a CLI-only AI coding workflow orchestrator; adding document processing, vector storage, and study tools would violate its single-responsibility boundary.
- Implementation: Standalone project at
/home/pontes/projects/mind-forge/with its own package.json, tsconfig, and plugin entry point.
D-02: Interface Modality — MCP tools (ingest, query, generate) auto-invoked by the LLM.
- Rationale: NotebookLM-like workflow is conversational — user says "summarize this PDF" and the LLM calls the tool automatically. No slash commands needed.
- Implementation:
@modelcontextprotocol/sdkwithStdioServerTransport. 3 tools registered with JSON Schema input schemas.
D-03: Source Formats (MVP) — All: PDF, DOCX, Markdown, images (OCR), web URLs.
- Rationale: User wants full format support from the start.
- Implementation: 5 extractors in
src/extract/with auto-detection via file extension + URL pattern. Usespdf-parse/pdftotext,mammoth, native read,tesseract.js, and@mozilla/readability.
D-04: Embedding Approach — Local Ollama preferred (conditional ≤8GB RAM), fallback to LLM provider.
- Rationale: Ollama carries zero recurring cost and keeps data on-device. Abstraction layer allows future provider swaps.
- Implementation:
EmbeddingProviderinterface insrc/types.ts, factory insrc/embed/provider.ts. Ollama adapter viaollamanpm package, LLM adapter via OpenAI-compatible API.
D-05: Vector Storage — SQLite + sqlite-vec.
- Rationale: Single-user plugin needs no client-server vector DB. SQLite is zero-dependency, single-file, easy to back up.
- Implementation:
better-sqlite3with sqlite-vec extension. 768-dimension fixed (nomic-embed-text default). ANN search via sqlite-vec virtual table.
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 · 65 lines · 1,247 tokens per session scan A a21a5131db18
mind-forge AGENTS.md is an instructions file published in the GitHub repository goncalompontes/mind-forge (0 stars, last pushed 2mo ago), licensed MIT. It adds 1,247 tokens to every session, about $0.0062 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.