Engram Memory Protocol
- 175 installs
- 5.8k repo stars
- Updated July 30, 2026
- gentleman-programming/engram
Part of the Engram spec-driven development system, oriented toward a memory protocol that persists context for the coding agent across the workflow.
About
An Engram skill within a spec-driven development toolkit that supports coordinating spec, design, implementation, and validation. A developer uses it to apply Engram's memory protocol for retaining agent context.
- Part of the Engram spec-driven development skill set
- Focused on an agent memory protocol
Engram Memory Protocol by the numbers
- 175 all-time installs (skills.sh)
- Ranked #3,092 of 16,546 AI & Agent Building skills by installs in the Skillselion catalog
- Data as of Aug 5, 2026 (Skillselion catalog sync)
npx skills add https://github.com/gentleman-programming/engram --skill engram-memory-protocolAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 175 |
|---|---|
| repo stars | ★ 5.8k |
| Last updated | July 30, 2026 |
| Repository | gentleman-programming/engram ↗ |
What it does
Part of the Engram spec-driven development system, oriented toward a memory protocol that persists context for the coding agent across the workflow.
Files
When to Use
Use this skill when:
- Starting non-trivial changes
- Coordinating spec, design, implementation, and validation
- Running command-based SDD flow
---
Canonical Phase Order
1. explore - understand existing behavior and constraints 2. propose - define intent and scope 3. apply - implement tasks from approved plan 4. verify - validate behavior against spec and regressions 5. archive - capture completion and close loop
Never skip a phase without explicit rationale.
---
Artifacts per Phase
- Explore: findings and risks
- Propose: change proposal with scope boundaries
- Apply: code + tests
- Verify: evidence of validation
- Archive: finalized summary and follow-ups
---
Exit Criteria
- [ ] Scope and risks understood before implementation
- [ ] Tests prove expected behavior
- [ ] Verification covers regressions
- [ ] Session summary captures learnings for next work
Related skills
Setup Matt Pocock SkillsScaffold the per-repo configuration that Matt Pocock’s engineering agent skills rely on so they understand the issue tracker, triage labels, and domain documentation la495k196k
Lark AppsConnect Claude, Cursor or custom agents directly to Lark (Feishu) for messaging, document automation, approval workflows and enterprise data access.402k
CavemanSlash token usage by roughly 75% while keeping every technical detail intact when working with Claude Code, Cursor or similar agents.391k94.7k
Lark Skill MakerQuickly turn any Lark/Feishu OpenAPI call or multi-step workflow into a reusable agent skill with its own SKILL.md.386k16k
Running Claude Code Via Litellm CopilotRun Claude Code at a fraction of the cost by routing requests through LiteLLM to the GitHub Copilot Chat API.270k72
Codex PetGenerate a complete Codex Pet spritesheet and metadata from one reference image without needing an OpenAI key or Codex Pro.246k10