engram-architecture-guardrails

engram-architecture-guardrails is a skill for Claude Code, Codex from Gentleman-Programming/engram. It costs 45 tokens per session (323 once invoked), scanned A, original, MIT.

A set of architecture rules for Engram, covering its local database, cloud synchronization, dashboard, and plugins. It defines which part of the system should own local data, cloud data, HTTP behavior, browser rendering, and background synchronization.

In plain words
What is it for?
Use it when adding subsystems, moving responsibilities, changing synchronization or persistence, or modifying local, cloud, dashboard, and plugin boundaries. It also requires regression tests for boundary changes and both sync directions.
Why use it?
It reduces unclear ownership and hidden connections between system parts, while preserving the rule that local SQLite is the source of truth and the cloud replicates it.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it when adding subsystems, moving responsibilities, changing synchronization or persistence, or modifying local, cloud, dashboard, and plugin boundaries. It also requires regression tests for boundary changes and both sync directions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/gentleman-programming/engram/architecture-guardrails
About the project

Engram is a local or cloud-backed memory system for AI coding agents, provided as a single Go binary with SQLite full-text search and interfaces including a command line, HTTP API, MCP server, and terminal UI. It helps compatible coding agents retain project decisions, bugs, conventions, and other useful context across sessions. The catalogue add-ons configure and operate Engram’s memory workflows.

Gentleman-Programming/engram · 6,364 stars · on GitHub · engram.gentlemanprogramming.com

Install

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.

Any agent
npx skills add Gentleman-Programming/engram --skill architecture-guardrails
Clone the repo
git clone --depth 1 https://github.com/Gentleman-Programming/engram

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for engram-architecture-guardrails

README.md
[![agentmods](https://agentmods.dev/badge/skills/gentleman-programming/engram/architecture-guardrails.svg)](https://agentmods.dev/skills/gentleman-programming/engram/architecture-guardrails)
Your own site
<a href="https://agentmods.dev/skills/gentleman-programming/engram/architecture-guardrails"><img src="https://agentmods.dev/badge/skills/gentleman-programming/engram/architecture-guardrails.svg" alt="Measured on agentmods" height="20"></a>
Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 323 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00045 $0.00323
Opus 5 $0.00023 $0.00161
Sonnet 5 $0.00009 $0.00065
Haiku 4.5 $0.00005 $0.00032

Measured 8d ago against content hash eaeff9f5b640, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

engram-architecture-guardrails 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 8d 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.

skills/architecture-guardrails/SKILL.md · 47 lines

What it actually says

When to Use

Use this skill when:

  • Adding a new subsystem or major package
  • Moving responsibilities between local store, cloud, dashboard, or plugins
  • Changing sync flow, source-of-truth rules, or persistence boundaries

Core Guardrails

  1. Local SQLite is the source of truth; cloud is replication and shared access.
  2. Keep plugin/adaptor layers thin; real behavior belongs in Go packages.
  3. Prefer explicit boundaries: store, cloudstore, server, dashboard, autosync.
  4. New features must fit the existing local-first mental model before they fit the UI.
  5. Do not hide cross-system coupling inside helpers or templates.

Decision Rules

  • Local-only concern -> internal/store
  • Cloud materialization or org-wide control -> internal/cloud/cloudstore
  • HTTP contract or enforcement -> internal/cloud/cloudserver
  • Browser rendering and UX -> internal/cloud/dashboard
  • Background orchestration -> internal/cloud/autosync

Validation

  • Add regression tests for every boundary change.
  • Verify local, remote, and dashboard behavior still tell the same product story.
  • If the change touches sync, test both push and pull paths.
Changes

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.

  1. 8d ago First seen · 47 lines · 45 tokens per session scan A eaeff9f5b640

Subscribe to this mod's changes

engram-architecture-guardrails is a skill published in the GitHub repository Gentleman-Programming/engram (6,364 stars, last pushed today), licensed MIT. It adds 45 tokens to every session and 323 once invoked, about $0.0002 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 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens