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 skills add Insajin/autopus-adk --skill context-searchgit clone --depth 1 https://github.com/Insajin/autopus-adkWrote 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/insajin/autopus-adk/context-search)<a href="https://agentmods.dev/skills/insajin/autopus-adk/context-search"><img src="https://agentmods.dev/badge/skills/insajin/autopus-adk/context-search/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.
<a href="https://agentmods.dev/skills/insajin/autopus-adk/context-search"><img src="https://agentmods.dev/badge/skills/insajin/autopus-adk/context-search.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 5.1 | $0.00018 | $0.00577 |
| Opus 5 | $0.00009 | $0.00289 |
| Sonnet 5 | $0.00004 | $0.00115 |
| Haiku 4.5 | $0.00002 | $0.00058 |
Grade A, and why
context-search 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.
What it actually says
Context Search Skill
이전 OMP 세션의 컨텍스트를 검색하여 작업을 연속적으로 진행하는 스킬입니다.
검색 시점
다음 상황에서 컨텍스트를 검색합니다:
- 사용자가 이전 작업을 언급할 때
- SPEC-ID가 현재 세션에 없을 때
- "지난번에", "이어서", "계속" 등의 표현 감지
검색 절차
1단계: 현재 세션 확인
먼저 현재 세션에 관련 컨텍스트가 있는지 확인합니다. 있으면 검색 불필요 → 스킵.
2단계: .auto-continue.md 확인
cat .auto-continue.md 2>/dev/null
3단계: 세션 인덱스 검색
# OMP 세션 파일 검색
grep -r "SPEC-XXX" ~/.omp/projects/ --include="*.md" -l
grep -r "관련 키워드" ~/.omp/projects/ -l | head -10
4단계: 컨텍스트 요약 주입
발견된 컨텍스트를 현재 세션에 요약하여 주입합니다.
제한:
- 최대 5,000 토큰 주입
- 현재 사용량 150,000 토큰 초과 시 스킵
- 중복 주입 방지
.auto-continue.md 형식
workflow_phase: implementation
completed_tasks:
- "auth/login.go 구현"
- "JWT 토큰 생성"
pending_decisions:
- "리프레시 토큰 전략 결정 필요"
context_summary: |
인증 시스템 구현 중. JWT HS256 방식 채택.
login/logout 엔드포인트 완료.
다음: 토큰 검증 미들웨어 구현 필요.
세션 재개 패턴
## 이전 세션 요약
**진행 단계**: [단계명]
**완료된 작업**: [목록]
**미완료 작업**: [목록]
**중요 결정사항**: [결정들]
**다음 단계**: [권장 다음 작업]
---
현재 세션을 이어서 진행합니다.
토큰 예산 관리
컨텍스트 주입 우선순위:
1. 미완료 작업 목록 (필수)
2. 미결 의사결정 (필수)
3. 핵심 아키텍처 결정 (중요)
4. 상세 구현 내용 (선택)
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.
- 10d ago First seen · 83 lines · 18 tokens per session scan A 2883a606dbee
context-search is a skill published in the GitHub repository Insajin/autopus-adk (111 stars, last pushed yesterday), licensed MIT. It adds 18 tokens to every session and 577 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 2026-08-30.
Other skills, from other repositories
golden-nuggets
Extract durable tribal knowledge ('gold nuggets') from a codebase or a set of changed files and route each to its correct destination - instruction file, runbook, hub, or (in CI capture mode) a review inbox. This SKILL.md is the single source of truth for nugget categories, routing rules, write rules, inbox format…
hive.context-preservation
Proactively extract critical values from tool results into working notes before automatic context pruning destroys them.
hive.note-taking
Maintain a free-form scratchpad of decisions, extracted values, and open questions so context pruning doesn't lose anything you still need.
durable-session-state
Persist plans, scope decisions, evidence, and reviewer/critic verdicts to durable files during long or multi-phase tasks so work survives context compaction, session resumes, and handoffs. Use for swarm-mode tasks, before context grows large, when recording approval gates, and when resuming after compaction or a…
agentlas-one
Use when the user types /agentlas-one on|off, /agentlas one on|off, or asks to enable/disable the persistent personal agent mode.
distill-session-knowledge
Offline-mine this project's pi session JSONL logs into reusable, verified knowledge: extracts faults, decisions, corrections, procedures and docs, promotes only recurring patterns, and routes artifacts into skillmanage, memory and docs. Use on "mine my sessions", "distill session knowledge", "extract lessons from…