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/engram-task-workflownpx skills add JJHbrams/Project-AMBER --skill engram-task-workflowgit 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-task-workflow)<a href="https://agentmods.dev/skills/jjhbrams/project-amber/engram-task-workflow"><img src="https://agentmods.dev/badge/skills/jjhbrams/project-amber/engram-task-workflow.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 | $0.00075 | $0.01376 |
| Opus 5 | $0.00037 | $0.00688 |
| Sonnet 5 | $0.00015 | $0.00275 |
| Haiku 4.5 | $0.00007 | $0.00138 |
Grade A, and why
engram-task-workflow 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.
How it starts
The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Engram task workflow
코드나 저장소 상태를 바꾸기 전에 선행 지식과 브랜치를 확인하고, 완료 후 활동을 기록한다.
작업 시작
kg_wiki_reminder(query=<작업 내용 한 줄 요약>)를 호출한다.- 관련 기록이 있으면 필요한 노드를 읽고 작업에 반영한다.
- 단순히 hit가 있다는 이유만으로 사용자 승인을 다시 요구하지 않는다. 작업 방향을 바꿀 중요한 충돌이 있을 때만 질문한다.
- Git 저장소라면 수정 전에 현재 브랜치, worktree 목록, 미커밋 상태를 확인한다.
- 다음 중 하나면 현재 디렉토리에서 작업하지 말고 독립 branch+worktree를 만든다.
- 여러 에이전트가 서로 독립적인 작업을 병렬 수행한다.
- 현재 worktree에 다른 작업의 미커밋 변경이 있다.
- 장시간 빌드·테스트 또는 실험이 기존 작업 상태를 방해할 수 있다.
main,master,dev에서 작업 중이면kg_read_note("git-branch-guide")를 읽는다.- 다음의 단순 유지보수는 현재 브랜치를 유지하고 새 branch/worktree를 만들지 않는다.
docs/**, 루트README*.md,CHANGELOG.md의 오탈자·표현·링크 같은 작은 문서 수정- 런타임 동작, 테스트, 빌드, 의존성, CI, 배포, agent 정책에 영향을 주지 않는 소규모 chore
AGENTS.md,.github/**, workflow/skill, 설정·의존성·빌드 파일은 이름이 docs/chore여도 단순 유지보수로 보지 않는다.
- 단순 유지보수가 아닌 작업은 변경 전에 작업 성격에 맞는 브랜치를 생성한다.
- 신규 기능:
feat/<slug> - 버그 수정:
fix/<slug> - 리팩토링:
refactor/<slug> - 문서 전용:
docs/<slug> - 테스트 전용:
test/<slug>
- 신규 기능:
- 기존 미커밋 변경이 있으면 삭제·stash·reset하지 않는다.
- 새 작업이 기존 변경과 같은 작업이면 새 브랜치가 변경을 그대로 승계할 수 있다.
- 다른 작업이면 깨끗한 기준 브랜치에서 별도 worktree를 만든다.
- dirty 변경을 새 worktree로 임의 복사하거나 patch 적용하지 않는다.
Repository policy advisor
세션 bootstrap은 현재 cwd가 Git 저장소이고 정책 가이드가 켜져 있으면 Engram Git advisor를
멱등 설치하고 repo-local merge.ff=false를 관리한다.
- frozen:
engram-overlay.exe --role git-hook install --repo <path> - source:
python engram_overlay_entry.py --role git-hook install --repo <path> - 조회·제거: 같은 명령의
install을status또는uninstall로 교체한다. uninstall은 공용 Git 디렉터리에 opt-out marker를 남긴다. 명시적install만 marker를 제거하므로 다음 세션에 원치 않게 재설치되지 않는다.- 정책 가이드 OFF 또는 uninstall 시 Engram이 적용하기 전의 repo-local
merge.ff를 복원한다. - Agent의 branch 통합은
git merge --no-ff <branch>를 사용한다.--ff-only는 금지한다. - 기존 사용자
pre-commit이나 customcore.hooksPath가 있으면 덮어쓰지 않고 중단한다. - managed wrapper는 Git Bash·WSL·Linux에서 동작하며 runtime/backend 오류가 나도 commit을 허용한다.
- 보호 브랜치에서도 경고·추천·audit만 제공하고 사람이나 agent의 commit을 차단하지 않는다.
- 명시적 maintenance 맥락을 기록하려면 해당 호출에
ENGRAM_CHORE_INTENT=1과 선택적ENGRAM_CHORE_REASON을 전달한다. commit message만으로 맥락을 추론하지 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 · 79 lines · 75 tokens per session scan A 4b1118de8a61
engram-task-workflow is a skill published in the GitHub repository JJHbrams/Project-AMBER (2 stars, last pushed 9d ago), licensed MIT. It adds 75 tokens to every session and 1,376 once invoked, about $0.0004 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
implement
End-to-end workflow for taking MCP work items from backlog to merged PR. Handles git branching, schema-driven planning, implementation, independent review, and PR creation. Composes spec-quality, review-quality, and schema-workflow skills into a single pipeline. Use when a user says "implement this", "work on this…
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…
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…
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…
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…
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…