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/lucasmella-stack/mismem/copilot-instructionsgit clone --depth 1 https://github.com/lucasmella-stack/misMEMWhat 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 | $0.01119 | $0.01119 |
| Opus 5 | $0.00560 | $0.00560 |
| Sonnet 5 | $0.00224 | $0.00224 |
| Haiku 4.5 | $0.00112 | $0.00112 |
Grade A, and why
misMEM copilot-instructions.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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Copilot Instructions — misMEM
Sistema de memoria persistente con MCP (3 capas: episodes \u2192 memories \u2192 traits).
Stack
- Engine: Node 22, TypeScript strict ESM, better-sqlite3, MCP SDK, Zod, FTS5
- Tests: Vitest. Correr
pnpm testdesdeengine/antes de commitear - Build:
pnpm build(tsc \u2192dist/) - Container:
mismem-brain(Alpine multi-arch), expone HTTP/SSE en:3200 - Deploy: Docker en un VPS detrás de Traefik (ver
DEPLOY.md)
Convenciones de c\u00f3digo
- TypeScript estricto: nunca
any, prefer\u00ed tipos expl\u00edcitos - Validar todo input externo con Zod (ver
engine/src/schema.ts) - Funciones puras + DI para testabilidad (ej.
distillFnenconsolidation/run.ts) - ESM: imports con extensi\u00f3n
.jsaunque el archivo sea.ts - IDs: ULID (libreria
ulid) - DB: better-sqlite3 sincr\u00f3nico, todo dentro de
db.transaction(() => ...) - Comentarios solo PARA QU\u00c9, nunca QU\u00c9
- Nombres y c\u00f3digo en ingl\u00e9s; mensajes de log/UI en espa\u00f1ol
Esquema (resumen)
episodes(id, scope, body, created_at, consolidated_into)— verbatim, body NOtextmemories(id, scope, gist, details, source_episode_ids JSON, salience, created_at, last_accessed_at)traits(id, scope, name, evidence_memory_ids JSON, strength, polarity, created_at, updated_at)- FTS5 virtual:
episodes_fts(body),memories_fts(gist, details),traits_fts(name)
MCP tools (en engine/src/tools.ts)
capture(scope, body)\u2192 inserta episoderecall(query, scope?, limit?)\u2192 ranking traits>memories>episodes + Hebbian salience refreshconsolidate(scope, gist, details?, source_episode_ids[])\u2192 crea memory + marca episodescrystallize(scope, name, evidence_memory_ids[], polarity?)\u2192 crea traitforget(scope?, ttl_days?, salience_threshold?)\u2192 purga episodes consolidados + memories de baja salience
Reglas de seguridad
- NUNCA leer/editar
.env*. Tampoco mostrar secrets en respuestas - NUNCA ejecutar
git push --force,git reset --hard,Remove-Item -Recursesin pedir - NUNCA modificar
schema.tssin migration plan (rompe DB en producci\u00f3n) - Validar inputs en bordes (Zod en MCP handlers, ya hecho)
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 · 68 lines · 1,119 tokens per session scan A 52c4c7d6b09f
misMEM copilot-instructions.md is an instructions file published in the GitHub repository lucasmella-stack/misMEM (3 stars, last pushed 1mo ago), licensed MIT. It adds 1,119 tokens to every session, about $0.0056 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
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.
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).
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.