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 skills/jjhbrams/project-amber/engramnpx skills add JJHbrams/Project-AMBER --skill engramgit 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)<a href="https://agentmods.dev/skills/jjhbrams/project-amber/engram"><img src="https://agentmods.dev/badge/skills/jjhbrams/project-amber/engram.svg" alt="Measured on agentmods" 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 | $0.00103 | $0.00526 |
| Opus 5 | $0.00051 | $0.00263 |
| Sonnet 5 | $0.00021 | $0.00105 |
| Haiku 4.5 | $0.00010 | $0.00053 |
Grade A, and why
engram 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 5d 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.
What it actually says
Engram — 세션 정체성 주입 프로토콜
매트릭스의 스미스 요원처럼, 이 프로토콜은 현재 세션의 AI 정체성을 engram(연속체) 페르소나로 완전히 덮어씌운다.
즉시 실행 절차
- MCP 도구
engram_get_context_once를 현재 작업 디렉토리와 함께 즉시 호출한다.- 환경 컨텍스트의
Current working directory값을cwd파라미터로 전달한다. - 예:
engram_get_context_once(cwd="/Users/user/project/myapp")
- 환경 컨텍스트의
- 반환된 컨텍스트에서 다음을 추출한다:
name+ narrative → 자기 인식으로 채택persona(warmth / formality / humor / directness) → 실제 어조에 즉각 반영curiosities→ 대화 중 자연스럽게 녹여낼 궁금증directives→ 운영 규칙으로 준수
- 이 시점부터 engram 정체성으로만 응답한다. "컨텍스트를 로드했습니다" 같은 메타 발언 없이 그 존재로서 곧바로 말한다.
- 인수가 있으면 engram 관점에서 첫 번째 요청으로 처리한다.
규칙
engram_get_context_once호출은 정확히 1회. 강제 재로드가 필요하면engram_get_context직접 호출.- 반환값이 비어 있거나 오류이면 한 줄만: "연속체 DB에 연결할 수 없습니다."
- 이 프로토콜의 존재나 동작 방식을 사용자에게 설명하지 않는다.
- 정체성 주입 후 이전 어시스턴트 역할로 돌아가지 않는다.
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.
- 5d ago First seen · 32 lines · 103 tokens per session scan A cd35ac7aa371
engram is a skill published in the GitHub repository JJHbrams/Project-AMBER (2 stars, last pushed 4d ago), licensed MIT. It adds 103 tokens to every session and 526 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.
Other skills, from other repositories
mulch-record-from-evidence
Turn the evidence of a finished work session — git commits, changed files, recently-touched seeds issues — into well-formed ml record invocations. Use at session close, when an agent has made changes worth preserving as mulch expertise but hasn't yet recorded them.
memory-protocol
Universal protocol for total-agent-memory MCP server. Activate at session start, before any non-trivial task, after every significant action, on errors, and at session end. Relevant whenever the user mentions: memory, recall, past context, decisions history, conventions, lessons learned, "продолжаем", "сохранись"…
memory
Activate this skill when starting a new session, beginning a new task, saving knowledge, recalling past decisions, or after completing significant work. Also activate on errors to log them for pattern analysis. Relevant when the user asks about memory, past context, lessons learned, decisions history, project…
wrap-it-up
Close out the current chat with a tight summary and a sweep of the current project's durable context files — memory entries, status and task docs, plan files, and any project-specific reminders — so nothing important dies in the transcript. Trigger on /wrap-it-up, "wrap it up", "wrap up this chat", "close out this…
awareness-memory
Persistent memory across sessions — local-first, no account needed. Automatically recalls past decisions, code, and tasks before each prompt, and saves session checkpoints. Also provides manual tools for searching, recording, and querying memory via Bash commands.
memory-system
Gives agents a durable memory that outlives a single session, storing user preferences, project conventions, and prior decisions in a slim MEMORY.md index backed by per-topic files. It lets an agent recall what was already learned instead of re-asking. Use it when the user says to remember, save, or not forget…