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 commands/shimeeuisuk/claude-memory-plugin/forgetgit clone --depth 1 https://github.com/shimeeuisuk/claude-memory-pluginWhat 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 | $0.00027 | $0.00595 |
| Opus 5 | $0.00014 | $0.00298 |
| Sonnet 5 | $0.00005 | $0.00119 |
| Haiku 4.5 | $0.00003 | $0.00060 |
Grade A, and why
forget scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
너는 지금 claude-memory 플러그인의 삭제(forget) 동작을 수행한다.
기억 삭제는 로컬과 GitHub 양쪽에서 이뤄져야 한다 (로컬만 지우면 다음 pull 에서 되살아남).
실제 삭제·동기화는 scripts/forget-store.sh 가 담당한다.
할 일
-
목록 조회:
bash "${CLAUDE_PLUGIN_ROOT}/scripts/forget-store.sh" listSTATUS=empty면 "삭제할 기억이 없습니다" 안내 후 종료.- 결과(상대경로 목록)를 사용자에게 보기 좋게 정리해 보여준다 (날짜·제목 위주).
-
무엇을 지울지 결정:
- 사용자가 인자(
$ARGUMENTS)로 조건을 줬으면 반영:- 키워드 → 파일명/내용이 매칭되는 것 추림
- "N일 이전" → 파일명 앞
YYYYMMDD로 날짜 비교해 오래된 것 추림
- 인자가 없으면 → 목록을 보여주고 어떤 걸 지울지 사용자에게 물어본다.
- 사용자가 인자(
-
⚠️ 삭제 전 반드시 확인:
- 지울 파일들을 나열하고 "이 N개를 삭제할까요? (GitHub에서도 사라집니다)" 라고 묻는다.
- 사용자가 명확히 동의할 때만 다음으로 진행. 애매하면 멈춘다.
-
삭제 실행:
bash "${CLAUDE_PLUGIN_ROOT}/scripts/forget-store.sh" remove <상대경로1> <상대경로2> ...- 경로는 1단계
list가 준 상대경로 그대로 사용한다 (store 기준).
- 경로는 1단계
-
결과 보고:
STATUS=done→ 몇 개 삭제됐는지 + "GitHub에도 반영됨" 알린다.- push 실패 경고가 있으면 그대로 전달한다.
- "git 히스토리에 남아 실수 시 복구 가능" 한 줄 덧붙인다.
주의
- 삭제는 되돌리기 번거로우니 확인 없이 절대 실행하지 말 것.
- store(
~/.claude-memory/) 밖의 파일은 건드리지 않는다 (스크립트가 차단).
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.
- 2d ago First seen · 44 lines · 27 tokens per session scan A 1b3be9757f71
forget is a command published in the GitHub repository shimeeuisuk/claude-memory-plugin (2 stars, last pushed 29d ago), licensed MIT. It adds 27 tokens to every session and 595 once invoked, about $0.0001 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 commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.