Borrowing it
Nothing to install: this file belongs to JJHbrams/Project-AMBER. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/JJHbrams/Project-AMBER/master/.claude/skills/engram-rebuild/SKILL.mdgit clone --depth 1 https://github.com/JJHbrams/Project-AMBERWrote 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.
[](https://agentmods.dev/skills/jjhbrams/project-amber/engram-rebuild)<a href="https://agentmods.dev/skills/jjhbrams/project-amber/engram-rebuild"><img src="https://agentmods.dev/badge/skills/jjhbrams/project-amber/engram-rebuild/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/jjhbrams/project-amber/engram-rebuild"><img src="https://agentmods.dev/badge/skills/jjhbrams/project-amber/engram-rebuild.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00092 | $0.01032 |
| Opus 5.5 | $0.00037 | $0.00413 |
| Sonnet 5.5 | $0.00018 | $0.00206 |
| Haiku 4.5 | $0.00009 | $0.00103 |
Grade A, and why
engram-rebuild 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 1mo 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
engram 재빌드 · 배포
이미 설치가 끝난 환경에 코드 변경을 반영할 때 쓴다. 상세 근거는
docs/dev/system-technical-reference.md §10.
1. 먼저 판단
Python 소스(overlay/, core/, discord_bot/)를 개발 환경에서 확인할 때는
dev-rebuild.ps1 로 끝난다. 이 경로는 frozen exe를 만들지 않는다.
frozen 빌드는 멀티콜 바이너리라 같은 exe 가 --role 로 MCP 서버·kg-watcher 까지 겸한다
(engram_overlay_entry.py::_dispatch_backend_role). 모든 Python 소스가 exe 하나에
번들되므로 exe 교체 = 전 컴포넌트 갱신이다.
전체 INSTALL.ps1 이 필요한 경우 — 이때만:
| 변경 | 이유 |
|---|---|
requirements.txt / environment.yml |
PyInstaller 가 conda env 에서 패키지를 수집한다. env 에 없으면 번들에도 없음 |
shim(~/.engram/*.cmd) · PATH · 바로가기 |
설치 모듈 07/08/10 |
MCP 클라이언트 등록 · config/clients/*.md |
설치 모듈 05 |
DB 스키마 추가는 보통 예외 — core/storage/db.py 가 연결 시
CREATE TABLE IF NOT EXISTS 마이그레이션을 돌린다.
2. 실행
.\dev-rebuild.ps1 # source contract + source 재기동 + readiness
.\dev-rebuild.ps1 -NoStart # source contract만 확인
기존 source installer 호환 경로가 필요할 때:
.\INSTALL.ps1 # auto — mtime 비교로 필요할 때만 빌드
.\INSTALL.ps1 -OverlayBuildMode clean # 빌드 캐시 꼬임 정리
-OverlayBuildMode: auto(기본, mtime 비교) | rebuild(항상 증분) | clean(항상 clean) | skip(빌드 생략)
배포용 frozen bundle/installer는 다음 경로만 사용한다:
.\installer\build-installer.ps1
3. 실행 전 확인할 것
- 현재 STM 포트의 overlay 가 종료된다. STM 브로커·MCP 서버·kg-watcher 가 함께 내려가므로, 다른 CLI 세션이 engram MCP 를 쓰는 중이면 그 세션의 MCP 호출이 실패한다. 사용자에게 먼저 알리고 진행할 것.
dev-rebuild.ps1은 PyInstaller, embedding model packaging,dist/변경을 수행하지 않는다.-Deploy,-FreshBuild는 더 이상 지원하지 않으며 installer builder 사용 안내와 함께 실패한다.- 사용자 설정(
~/.engram/overlay.user.yaml)은 두 경로 모두 보존한다(없을 때만 생성).
4. 반영됐는지 확인
새 프로세스가 source entrypoint인지:
Get-CimInstance Win32_Process |
Where-Object CommandLine -like '*engram_overlay_entry.py*' |
Select-Object ProcessId, CommandLine
동작 확인은 로그가 가장 확실하다 — 새 코드의 로그 라인을 찾는다:
Get-ChildItem "$env:USERPROFILE\.engram\logs" -Filter "overlay-*.log" |
Sort-Object LastWriteTime -Descending | Select-Object -First 1
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.
- 1mo ago First seen · 93 lines · 92 tokens per session scan A c4b5e43a7b7f
engram-rebuild is a skill published in the GitHub repository JJHbrams/Project-AMBER (2 stars, last pushed 24d ago), licensed MIT. It adds 92 tokens to every session and 1,032 once invoked, about $0.0004 per session on Opus 5.5. 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 skills, from other repositories
penfield
Persistent memory for AI agents. Store decisions, preferences, and context that survive across sessions. Build knowledge graphs that compound over time. Hybrid search (BM25 + vector + graph) recalls what matters when you need it.
mengram-memory
Long-term memory with 3 types (facts, events, workflows). Remember user preferences, past conversations, and learned procedures across sessions. Use when recalling what the user said before, saving important info, getting user context, or tracking completed workflows.
memory-audit-discoverability
A review guide for checking whether stored memories can be found at the right time. It focuses on where memories are attached, when they are triggered, whether aliases are missing, and whether a parent has too many children.
memory-audit-pattern-extraction
A method for investigating repeated mistakes by comparing related memories and checking whether an earlier reminder failed. It looks at where the reminder was stored, when it was created, and whether it was strong enough to prevent the mistake.
memory-audit
An entry point for reviewing and maintaining an AI agent's stored memories. It describes how to remove repetition, preserve useful reasoning, and update memories when old conclusions no longer fit.
add-connector
Onboard a deus connect connector — a way to route Claude Code sessions to non-Claude models (e.g. GPT via CLIProxyAPI) alongside normal Claude access. Generic orchestrator over whichever connector is selected.