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/teamspwk/nova/strategic-compactnpx skills add TeamSPWK/nova --skill strategic-compactgit clone --depth 1 https://github.com/TeamSPWK/novaWrote 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/teamspwk/nova/strategic-compact)<a href="https://agentmods.dev/skills/teamspwk/nova/strategic-compact"><img src="https://agentmods.dev/badge/skills/teamspwk/nova/strategic-compact.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 | $0.00069 | $0.01693 |
| Opus 5 | $0.00034 | $0.00847 |
| Sonnet 5 | $0.00014 | $0.00339 |
| Haiku 4.5 | $0.00007 | $0.00169 |
Grade A, and why
strategic-compact 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Nova Strategic Compact
세션-수준 컨텍스트 압축 시점을 판단한다. NOVA-STATE 본문 스냅샷 + events.jsonl 분리(v5.44.0+ 상태-수준 모델)와 짝을 이루는 세션-수준 (Claude Code 컨텍스트 창 자체)의 /clear·/compact 적기를 안내한다. Nova 5기둥 중 맥락 기둥의 마지막 한 조각 — 진단(P0-1 컨텍스트 로스트 4원인 카탈로그)에서 자동 안내까지 잇는 출구.
적용 규칙 (on-demand 로드)
docs/nova-rules.md §8세션 상태 유지 — STATE 트림과 세션 압축의 분리docs/nova-rules.md §10관찰성 계약 — events.jsonl로 후험 검증 가능
핵심 원칙
- 상태-수준 ≠ 세션-수준. NOVA-STATE.md 본문 스냅샷 + events.jsonl 단일 진실원(
skills/context-chain/SKILL.md, v5.44.0+)은 사람-읽는 인덱스 + 기계-읽는 시계열이지 Claude 컨텍스트 창 압축이 아니다. 둘은 별도 트리거, 별도 효과. /clear≠/compact./clear는 무관 작업 사이 즉시 비움(요약 없음),/compact는 마일스톤 사이 요약 압축. 잘못 쓰면 Generator 컨텍스트가 회복 불가능하게 손실된다.- AI는 제안, 인간은 결정. 본 스킬은 시점 안내만 한다 —
/compact·/clear는 사용자가 직접 입력. 자동 실행 금지 (메모리feedback_evidence_first_identity정합). - 9 진입점 동결 유지. 본 스킬은 NOVA-STATE 갱신 트리거를 추가하지 않는다 (v5.19.6 state-prune-symmetry 룰 보존).
MUST TRIGGER (적기)
| 시점 | 권장 동작 | 사유 |
|---|---|---|
/nova:plan 완료 직후 |
/compact 권장 |
Plan 결과는 docs/plans/{slug}.md에 보존됨 — 컨텍스트는 요약해도 안전 |
/nova:design 완료 직후 |
/compact 권장 |
Design 결과는 docs/designs/{slug}.md에 보존됨 |
/nova:auto Phase 종료 시 |
/compact 권장 |
Phase 결과는 events.jsonl + v3 marker 자동 렌더로 보존됨 — 다음 Phase는 요약본만 있어도 충분 (v5.44.0+) |
| 토큰 사용량 70%+ 도달 | /compact 또는 /clear |
80%+ AUTOCOMPACT 발동 전 사용자 통제 압축 (docs/cost-optimization.md 권장 50%와 정합) |
| 무관 작업 전환 직전 | /clear |
어텐션 희석 사전 차단 (docs/context-rot-diagnosis.md §1 원인 1) |
| 에이전트 spawn 직전 (메인 토큰 70%+) | /compact |
서브에이전트 spawn 시 메인 컨텍스트가 과적이면 핸드오프 품질 저하 |
MUST NOT TRIGGER (금기)
| 시점 | 금지 사유 |
|---|---|
| 구현 sprint 도중 | Generator 컨텍스트 살아있어야 — Plan-Design 의도가 요약으로 손실되면 sprint 중간 일관성 붕괴 |
| Evaluator 검증 직전 | 적대적 검증은 같은 컨텍스트 재현 필요 — 압축 후 검증은 Generator-Evaluator 분리 원칙 훼손 |
| 블로커 분석 도중 | 블로커는 컨텍스트 의존적 — 압축 시 원인 추적 불가능 |
| 회귀 테스트 디버깅 도중 | 실패 메시지·스택은 원본 보존 가치 높음 |
컨텍스트 로스트 4 원인 매핑
docs/context-rot-diagnosis.md 4 원인별 1차 대응:
| 원인 | 대응 |
|---|---|
| 어텐션 희석 (Attention Dilution) | 무관 작업 전환 시 /clear |
| 명령 충돌 (Instruction Conflict) | /nova:check 정합성 검증 우선 (/compact로 해결 X) |
| 토큰 예산 압박 (Token Budget Pressure) | 70%+ 도달 시 /compact + MCP 비활성화 (P1-2 ≤10/80) |
| 관련성 미스매치 (Relevance Mismatch) | Explore 서브에이전트 분리 (/compact 무관) |
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 · 80 lines · 69 tokens per session scan A 28881883da3b
strategic-compact is a skill published in the GitHub repository TeamSPWK/nova (2 stars, last pushed 4d ago), licensed MIT. It adds 69 tokens to every session and 1,693 once invoked, about $0.0003 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
memory-recall
Search and recall relevant memories from past sessions via memsearch. Use when the user's question could benefit from historical context, past decisions, debugging notes, previous conversations, or project knowledge -- especially questions like 'what did I decide about X', 'why did we do Y', or 'have I seen this…
alive:session-history
Revive sessions (quick or heavy), browse, and search — 'what happened recently?', 'find the session where we discussed X', 'revive yesterday's session'. For single-session recall and multi-session browsing. If the human needs to merge multiple sessions into one working context or detect conflicts between parallel…
cross-session-handoff
Read, write, snapshot, and lock .arcgentic/state.yaml across planner, dev, audit, and optional test sessions.
recall
Must be used at the start of any non-trivial task involving code changes, debugging, repo exploration, file inspection, or environment/tooling investigation to surface stored guidance before analysis or tool use.
cco-templates
Manage context templates for common task types.
knowledge-priming-refiner
Facilitate a structured conversation to create a project-specific knowledge base document. Produces a knowledge-base.md that primes AI with the project's tech stack, architecture, trusted sources, and project structure. Use when the user says 'set up knowledge base', 'prime the project', 'onboard AI', 'create…