Project-AMBER: Skill for Claude Code

.claude/skills/engram-rebuild/SKILL.md

engram-rebuild is a skill for Claude Code from JJHbrams/Project-AMBER. It costs 92 tokens per session (1,032 once invoked), scanned A, original, MIT.

A rebuild and deployment guide for applying code changes to an already installed Engram environment. It determines whether to refresh the source version or rebuild the packaged executable.

In plain words
What is it for?
Use it after changing Engram’s Python code, dependencies, command shims, shortcuts, MCP client registrations, or packaged executable. It helps choose and run the appropriate rebuild or installation command.
Why use it?
It prevents using an unnecessarily large installation process when a source rebuild is enough, while identifying changes that require a full reinstall. This reduces the chance that updated code or settings remain missing from the installed copy.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is JJHbrams/Project-AMBER's own configuration. It tells Claude Code how to work on Project-AMBER itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Project-AMBER configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/JJHbrams/Project-AMBER/master/.claude/skills/engram-rebuild/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/JJHbrams/Project-AMBER

Made for: Claude Code.

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-rebuild

README.md
[![agentmods](https://agentmods.dev/badge/skills/jjhbrams/project-amber/engram-rebuild/github.svg)](https://agentmods.dev/skills/jjhbrams/project-amber/engram-rebuild)
Your own site
<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.

agentmods 80×15 button for engram-rebuild

Your own site · 80×15
<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>
Per session 92 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,032 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.
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 $0.00092 $0.01032
Opus 5 $0.00046 $0.00516
Sonnet 5 $0.00018 $0.00206
Haiku 4.5 $0.00009 $0.00103

Measured 10d ago against content hash c4b5e43a7b7f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

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 10d 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.

.claude/skills/engram-rebuild/SKILL.md · 93 lines

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

Read the full file on GitHub · 93 lines

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. 10d ago First seen · 93 lines · 92 tokens per session scan A c4b5e43a7b7f

Subscribe to this mod's changes

engram-rebuild is a skill published in the GitHub repository JJHbrams/Project-AMBER (2 stars, last pushed 3d ago), licensed MIT. It adds 92 tokens to every session and 1,032 once invoked, about $0.0005 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.

Related

Other skills, from other repositories

ralph

Launcher for the Ralph-style queue drain script — emits the right node ralph-loop.mjs invocation based on the user's filter and bounds. The actual loop runs as a Node script that spawns one claude -p --worktree per iteration; this skill is the configurator, not the loop. Use when a user says: drain the backlog, ralph…

jpicklyk/task-orchestrator · 99 tokens

adopt-project-scope

Migrates an already-populated, unscoped Task Orchestrator database in place to the project-scoping convention — creates a project anchor root, re-parents existing work trees under it, and writes rootId back to config.yaml. Use when a user says: adopt project scope, migrate this database to project scoping, make this…

jpicklyk/task-orchestrator · 99 tokens

review-proposals

Triages pending improvement-proposal MCP items — presents each with its scope and evidence, collects an accept/reject/defer decision per proposal, and carries out the disposition: project-scoped acceptances get their exact YAML applied to .taskorchestrator/config.yaml and pushed per-root; global acceptances get a…

jpicklyk/task-orchestrator · 129 tokens

work-summary

Generates a project dashboard from MCP work items. Default is a lean, attention-first view: what's in flight, what's blocked, what to do next, what's queued. Use when the user says: project status, what's active, show me the dashboard, work summary, what should I work on, project health, what's blocked, where did I…

jpicklyk/task-orchestrator · 110 tokens

manage-schemas

Creates, views, edits, deletes, and validates note schemas for the MCP Task Orchestrator in .taskorchestrator/config.yaml — the templates that define which notes agents must fill at each workflow phase. Also recommends schema designs from a library of workflow patterns (autonomous coding loops, spec-driven teams…

jpicklyk/task-orchestrator · 212 tokens

status-progression

Navigates role transitions for MCP work items using advanceitem. Shows current role, gate status, required notes, and the correct trigger to use. Use when a user says: advance this item, move to work, start this task, complete this item, what's the next status, why can't I advance, unblock this, cancel this item, or…

jpicklyk/task-orchestrator · 77 tokens