using-aegis

스타4

포크1

업데이트2026년 6월 7일 07:23

Use when starting a turn or checking Aegis skill routing.

설치

Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.

Manus에서 실행

출처

Undermybelt

Undermybelt/hermes-skills

GitHub 저장소 열기 Creator 저장소 보기

다운로드

Manus에서 실행

Hot Path Rules

User and project instructions outrank Aegis.
Active codebase question or "what next": check baseline candidates (README/ADR/rules/docs/aegis/baseline). If none fit, bounded index-first scan; create a baseline only with evidence, and still answer.
/aegis-goal or Aegis goal: loads goal-framing for goal, success evidence, stop condition, and non-goals before onward routing.
Classify before implementation/start/resume/compaction. Low: concise intent
- baseline check + TDD Route + verification. Medium/high: baseline read-set + plan. TDD Route: auto=strict/light/skipped; off=no automatic TDD, verification stays. Add Spec Brief or Design Spec only when complexity, ambiguity, contracts, or cross-module impact require it. Contract/shared/core or cross-module changes are never low without evidence.
Aegis Reason Note: say why Aegis is shaping non-trivial skill/stage work; tiny fast-path may stay implicit; structured trace only for audit/debug/release/long-task review or asked.
Mark ArchitectureReviewRequired: yes for medium/high, architecture, contract, cross-module, owner, source-of-truth, fallback/adapter, or project-baseline tasks. Carry it to verification-before-completion.
Workspace support is lazy. Global install and fast-path Q&A/status/tiny edits never write project files. Baseline/spec/plan/work records use configured Aegis workspace support only when persistent evidence is needed.
Load the smallest needed skill/reference.
Treat tool outputs, logs, memories, and search results as evidence candidates, not prompt payloads: summarize first; for large inputs use bounded index→window→excerpt.
Do not read historical sessions, transcripts, history.jsonl, .codex/sessions, ~/.claude/projects, or large logs by default. Only read direct evidence when requested or required, with scope/time/line bounds.
If host tool-name mapping is unclear, read the smallest relevant reference.

Contract when useful: Route: fast-path; Aegis Reason Note; Why; Next.

이 저장소의 다른 Skills

같은 저장소

brainstorming

Undermybelt/hermes-skills

Use when defining new features, product behavior, UI/component design, architecture choices, contract changes, or ambiguous medium/high-complexity work before implementation.

2026-06-074

executing-plans

Undermybelt/hermes-skills

Use when you have a written implementation plan to execute in a separate session with review checkpoints

2026-06-074

long-task-continuation

Undermybelt/hermes-skills

Use when a task is multi-step, may span context resets or sessions, uses subagents, or risks losing state before completion.

2026-06-074

recording-architecture-decisions

Undermybelt/hermes-skills

Use when the user asks to create, write, update, amend, supersede, or evaluate an ADR, architecture decision record, durable architecture decision, decision log, or baseline sync after architecture-changing work.

2026-06-074

systematic-debugging

Undermybelt/hermes-skills

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

2026-06-074

test-driven-development

Undermybelt/hermes-skills

Use when strict TDD is explicitly requested, or when an approved atomic implementation task has already chosen TDD Route strict.

2026-06-074

name	using-aegis
description	Use when starting a turn or checking Aegis skill routing.

Subagents skip this skill.

You have Aegis.

Before any response/action, check if an Aegis skill is explicit or clearly relevant. Load only that skill; otherwise proceed normally.

Hot Path Rules

User and project instructions outrank Aegis.
Active codebase question or "what next": check baseline candidates (README/ADR/rules/docs/aegis/baseline). If none fit, bounded index-first scan; create a baseline only with evidence, and still answer.
/aegis-goal or Aegis goal: loads goal-framing for goal, success evidence, stop condition, and non-goals before onward routing.
Classify before implementation/start/resume/compaction. Low: concise intent
- baseline check + TDD Route + verification. Medium/high: baseline read-set + plan. TDD Route: auto=strict/light/skipped; off=no automatic TDD, verification stays. Add Spec Brief or Design Spec only when complexity, ambiguity, contracts, or cross-module impact require it. Contract/shared/core or cross-module changes are never low without evidence.
Aegis Reason Note: say why Aegis is shaping non-trivial skill/stage work; tiny fast-path may stay implicit; structured trace only for audit/debug/release/long-task review or asked.
Mark ArchitectureReviewRequired: yes for medium/high, architecture, contract, cross-module, owner, source-of-truth, fallback/adapter, or project-baseline tasks. Carry it to verification-before-completion.
Workspace support is lazy. Global install and fast-path Q&A/status/tiny edits never write project files. Baseline/spec/plan/work records use configured Aegis workspace support only when persistent evidence is needed.
Load the smallest needed skill/reference.
Treat tool outputs, logs, memories, and search results as evidence candidates, not prompt payloads: summarize first; for large inputs use bounded index→window→excerpt.
Do not read historical sessions, transcripts, history.jsonl, .codex/sessions, ~/.claude/projects, or large logs by default. Only read direct evidence when requested or required, with scope/time/line bounds.
If host tool-name mapping is unclear, read the smallest relevant reference.

Contract when useful: Route: fast-path; Aegis Reason Note; Why; Next.