with one click
iterative-retrieval
서브에이전트 컨텍스트 문제를 해결하기 위한 점진적 컨텍스트 검색 개선 패턴
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Menu
서브에이전트 컨텍스트 문제를 해결하기 위한 점진적 컨텍스트 검색 개선 패턴
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
| name | iterative-retrieval |
| description | 서브에이전트 컨텍스트 문제를 해결하기 위한 점진적 컨텍스트 검색 개선 패턴 |
| origin | ECC |
서브에이전트가 작업을 시작하기 전까지 필요한 컨텍스트를 알 수 없는 멀티 에이전트 워크플로우의 "컨텍스트 문제"를 해결합니다.
서브에이전트는 제한된 컨텍스트로 생성됩니다. 다음을 알 수 없습니다:
표준 접근법의 실패:
컨텍스트를 점진적으로 개선하는 4단계 루프:
┌─────────────────────────────────────────────┐
│ │
│ ┌──────────┐ ┌──────────┐ │
│ │ DISPATCH │─────│ EVALUATE │ │
│ └──────────┘ └──────────┘ │
│ ▲ │ │
│ │ ▼ │
│ ┌──────────┐ ┌──────────┐ │
│ │ LOOP │─────│ REFINE │ │
│ └──────────┘ └──────────┘ │
│ │
│ Max 3 cycles, then proceed │
└─────────────────────────────────────────────┘
후보 파일을 수집하기 위한 초기 광범위 쿼리:
// Start with high-level intent
const initialQuery = {
patterns: ['src/**/*.ts', 'lib/**/*.ts'],
keywords: ['authentication', 'user', 'session'],
excludes: ['*.test.ts', '*.spec.ts']
};
// Dispatch to retrieval agent
const candidates = await retrieveFiles(initialQuery);
검색된 콘텐츠의 관련성 평가:
function evaluateRelevance(files, task) {
return files.map(file => ({
path: file.path,
relevance: scoreRelevance(file.content, task),
reason: explainRelevance(file.content, task),
missingContext: identifyGaps(file.content, task)
}));
}
점수 기준:
평가를 기반으로 검색 기준 업데이트:
function refineQuery(evaluation, previousQuery) {
return {
// Add new patterns discovered in high-relevance files
patterns: [...previousQuery.patterns, ...extractPatterns(evaluation)],
// Add terminology found in codebase
keywords: [...previousQuery.keywords, ...extractKeywords(evaluation)],
// Exclude confirmed irrelevant paths
excludes: [...previousQuery.excludes, ...evaluation
.filter(e => e.relevance < 0.2)
.map(e => e.path)
],
// Target specific gaps
focusAreas: evaluation
.flatMap(e => e.missingContext)
.filter(unique)
};
}
개선된 기준으로 반복 (최대 3회):
async function iterativeRetrieve(task, maxCycles = 3) {
let query = createInitialQuery(task);
let bestContext = [];
for (let cycle = 0; cycle < maxCycles; cycle++) {
const candidates = await retrieveFiles(query);
const evaluation = evaluateRelevance(candidates, task);
// Check if we have sufficient context
const highRelevance = evaluation.filter(e => e.relevance >= 0.7);
if (highRelevance.length >= 3 && !hasCriticalGaps(evaluation)) {
return highRelevance;
}
// Refine and continue
query = refineQuery(evaluation, query);
bestContext = mergeContext(bestContext, highRelevance);
}
return bestContext;
}
Task: "Fix the authentication token expiry bug"
Cycle 1:
DISPATCH: Search for "token", "auth", "expiry" in src/**
EVALUATE: Found auth.ts (0.9), tokens.ts (0.8), user.ts (0.3)
REFINE: Add "refresh", "jwt" keywords; exclude user.ts
Cycle 2:
DISPATCH: Search refined terms
EVALUATE: Found session-manager.ts (0.95), jwt-utils.ts (0.85)
REFINE: Sufficient context (2 high-relevance files)
Result: auth.ts, tokens.ts, session-manager.ts, jwt-utils.ts
Task: "Add rate limiting to API endpoints"
Cycle 1:
DISPATCH: Search "rate", "limit", "api" in routes/**
EVALUATE: No matches - codebase uses "throttle" terminology
REFINE: Add "throttle", "middleware" keywords
Cycle 2:
DISPATCH: Search refined terms
EVALUATE: Found throttle.ts (0.9), middleware/index.ts (0.7)
REFINE: Need router patterns
Cycle 3:
DISPATCH: Search "router", "express" patterns
EVALUATE: Found router-setup.ts (0.8)
REFINE: Sufficient context
Result: throttle.ts, middleware/index.ts, router-setup.ts
에이전트 프롬프트에서 사용:
When retrieving context for this task:
1. Start with broad keyword search
2. Evaluate each file's relevance (0-1 scale)
3. Identify what context is still missing
4. Refine search criteria and repeat (max 3 cycles)
5. Return files with relevance >= 0.7
continuous-learning 스킬 - 시간이 지남에 따라 개선되는 패턴~/.claude/agents/의 에이전트 정의Track and report Claude Code token usage, spending, and budgets from the local ECC cost-tracker metrics log. Use when the user asks about costs, spending, usage, tokens, budgets, or cost breakdowns by model, session, or date.
Instinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves them into skills/commands/agents. v2.1 adds project-scoped instincts to prevent cross-project contamination.
Create reproducible, cross-platform (macOS/Linux) development environments with Flox, a declarative Nix-based environment manager. Use when setting up project toolchains for any language, installing system-level dependencies (compilers, databases, native libs like openssl/BLAS), pinning exact package versions for a team, running local services (PostgreSQL, Redis, Kafka), onboarding developers with one command, or solving 'works on my machine' problems — including agent/vibe-coding setups that need project-scoped tools without sudo. Also use when the user mentions .flox/, manifest.toml, flox activate, or FloxHub.
Commercial-grade Python installer expert for Windows: Nuitka extreme compilation, dist slimming, DLL footprint analysis, and Inno Setup packaging to ship the smallest, fastest installers. Use only for advanced packaging/optimization (minimal size, fast startup), not basic script-to-exe conversion. 中文触发:Nuitka 极限优化、Python 商业打包、极限编译 Python、dist 瘦身、DLL 分析、最小安装包、最快启动、商业级打包风格
Use when a brand needs to discover or articulate its identity through structured multi-session interviews. Covers purpose, positioning, audience, personality, voice, narrative, and founder-brand tension across 8 modules using laddering, 5 Whys, and projective techniques. Produces a resumable session with disk-persisted state and a master brandbook (90_SYNTHESIS.md).
Use when a brand needs to discover or articulate its identity through structured multi-session interviews. Covers purpose, positioning, audience, personality, voice, narrative, and founder-brand tension across 8 modules using laddering, 5 Whys, and projective techniques. Produces a resumable session with disk-persisted state and a master brandbook (90_SYNTHESIS.md).