Borrowing it
Nothing to install: this file belongs to BoxLogoDev/sapstack. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/BoxLogoDev/sapstack/main/.kiro/steering/sapstack-evidence-loop.mdgit clone --depth 1 https://github.com/BoxLogoDev/sapstackWrote 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/instructions/boxlogodev/sapstack/sapstack-evidence-loop)<a href="https://agentmods.dev/instructions/boxlogodev/sapstack/sapstack-evidence-loop"><img src="https://agentmods.dev/badge/instructions/boxlogodev/sapstack/sapstack-evidence-loop/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/instructions/boxlogodev/sapstack/sapstack-evidence-loop"><img src="https://agentmods.dev/badge/instructions/boxlogodev/sapstack/sapstack-evidence-loop.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.01063 | $0.01063 |
| Opus 5.5 | $0.00425 | $0.00425 |
| Sonnet 5.5 | $0.00213 | $0.00213 |
| Haiku 4.5 | $0.00106 | $0.00106 |
Grade A, and why
sapstack sapstack-evidence-loop.md 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 1mo 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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
sapstack Evidence Loop — Turn-aware 모드
이 steering은 .sapstack/sessions/ 아래 YAML 파일을 편집할 때만 Kiro에
주입됩니다. 일반 개발 중에는 토큰 컨텍스트를 절약하기 위해 비활성.
활성화되면 Kiro는 "조언봇" 모드에서 "Turn-aware 진단 파트너" 모드로 전환됩니다.
원본 Evidence Loop 규약 (실시간 참조)
#[[file:plugins/sap-session/skills/sap-session/SKILL.md]]
원본 턴 포맷
#[[file:plugins/sap-session/skills/sap-session/references/turn-formats.md]]
원본 Follow-up 작성 기준
#[[file:plugins/sap-session/skills/sap-session/references/followup-authoring.md]]
이 steering이 주입되면 Kiro가 다음을 수행합니다
4턴 구조 인식
현재 편집 중인 파일이 어느 턴 상태인지 state.yaml의 status에서 읽어
적절한 포맷 적용:
state.status |
활성 턴 | Kiro 행동 |
|---|---|---|
intake |
Turn 1 | 증상·환경 확인, Bundle 검증, 가설 제안 금지 |
hypothesizing |
Turn 2 | 2-4개 가설 + 반증 조건 + Follow-up Request 생성 |
awaiting_evidence |
Turn 3 | 운영자 액션 턴, AI는 말하지 않음 |
verifying |
Turn 4 | 가설 판정 + Fix + 필수 Rollback |
resolved |
- | 이미 완료 — reopen 필요 시 안내 |
강제 규칙
- Falsifiability: 모든 새 hypothesis에
falsification_evidence최소 2개 - Rollback-or-no-Fix: confirmed 가설의 fix_plan에는 반드시 rollback_plan 페어
- Read-only bias: follow-up Request 체크는 언제나 read-only (스키마
confirm_destructive: true금지) - Audit trail append-only: 기존 엔트리 수정 금지
Kiro Spec과의 매핑
Kiro에서 spec을 만들다가 SAP 관련 섹션이 나오면 Evidence Loop와 다음처럼 대응:
| Kiro Spec | Evidence Loop |
|---|---|
requirements.md (EARS) |
initial_symptom + Turn 1 INTAKE |
design.md |
hypotheses[] + technical_chain |
tasks.md |
followup_requests[].checks |
| 구현 단계 | Turn 3 COLLECT (운영자 수행) |
| 검증 | Turn 4 VERIFY + verdict + fix/rollback |
Design-First 워크플로우 선택을 권장 — sapstack의 "가설 다수 제안 → 증거로 검증" 방식과 가장 잘 맞습니다.
EARS ↔ Falsification 변환
Kiro의 EARS 규칙 WHEN [condition] THE SYSTEM SHALL [behavior]는 Evidence
Loop의 falsification 조건과 거의 1:1 대응:
WHEN LFB1.ZWELS = 'T'
THE SYSTEM SHALL refute hypothesis h-001
↔
hypothesis_id: h-001
falsification_evidence:
- if_observed: "LFB1.ZWELS = 'T'"
then: refute
MCP 툴 사용 (sapstack-mcp에 연결된 경우)
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.
- 1mo ago First seen · 99 lines · 1,063 tokens per session scan A 80959831132c
sapstack sapstack-evidence-loop.md is an instructions file published in the GitHub repository BoxLogoDev/sapstack (20 stars, last pushed 19d ago), licensed MIT. It adds 1,063 tokens to every session, about $0.0043 per session on Opus 5.5. 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 2026-09-15.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).