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 kohj1018/agentic-dev-harness --skill amend-ssotgit clone --depth 1 https://github.com/kohj1018/agentic-dev-harnessWrote 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/kohj1018/agentic-dev-harness/amend-ssot)<a href="https://agentmods.dev/skills/kohj1018/agentic-dev-harness/amend-ssot"><img src="https://agentmods.dev/badge/skills/kohj1018/agentic-dev-harness/amend-ssot/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/kohj1018/agentic-dev-harness/amend-ssot"><img src="https://agentmods.dev/badge/skills/kohj1018/agentic-dev-harness/amend-ssot.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 | $0.00061 | $0.02675 |
| Opus 5 | $0.00030 | $0.01337 |
| Sonnet 5 | $0.00012 | $0.00535 |
| Haiku 4.5 | $0.00006 | $0.00267 |
Grade A, and why
amend-ssot 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 8d 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
이 skill은 이미 확정된 정본 문서의 부분 개정만 한다. 빈 문서를 채우거나(authoring), 발굴·스택 결정·시안 라운드를 돌지 않는다 — 그것은 각 bootstrap skill 소유다.
Codex: 본 skill은 wrapper 미보유(자연어 호출) — "Follow .claude/skills/amend-ssot/SKILL.md"로 호출한다(목록 SSOT = README, ADR-010#amend-3).
입력:
$ARGUMENTS의 따옴표 문자열 = 변경 요청(무엇을 어떻게 바꿀지).--from <출처>(선택) — 이 변경이 어디서 나왔는지.사용자/T-NNN/ finding ID.--dry-run(선택) — change-set만 출력하고 파일을 쓰지 않는다.- 기본 동작은 적용이다. 사용자 호출 자체가 적용 의도이므로 별도 승인 플래그를 두지 않는다.
A0. 변경 요청 정규화
자연어 요청을 «어느 정본의 어느 절이 어떻게 바뀌는가»의 change-set으로 바꾼다. 대상 정본은 넷뿐이다 — docs/10-charter/DISCOVERY.md · docs/10-charter/PROJECT_CHARTER.md · docs/20-system/ARCHITECTURE_OVERVIEW.md · docs/20-system/DESIGN.md.
- ADR은 대상이 아니다.
docs/90-decisions/**/ADR-*.md의 개정은 amend vs supersede 임계(ADR-045 D6)와 작성 주체·시점 트리거(ADR-000#amend-2)가 별도로 규율하며, boilerplate ADR은 fork 후 read-only이고 project ADR로 supersede하는 경로가 정해져 있다. ADR 개정 요청을 받으면 그 경로를 안내하고 종료한다. - 대상 절을 특정할 수 없으면 추측하지 않고 후보 2~3개를 제시해 사용자에게 묻는다.
- 대상 파일이 없으면(예: 비-UI 프로젝트의 DESIGN.md) 그 사실을 알리고 종료한다.
A1. 분류 (ADR-069 D2)
change-set을 넷 중 하나로 분류한다.
- editorial — 오탈자·표현·형식.
- local semantic — 한 절 안에서 의미가 바뀌나 A3 전파표에 걸리지 않음.
- cross-SSOT — A3 전파표에 걸림.
- foundation — 아래 라우팅 목록에 해당 → 거부하고 종료한다.
foundation 라우팅 (ADR-069 D4 — 절-키 고정. 판단이 아니라 열거다)
| 트리거 | 안내할 명령 |
|---|---|
DISCOVERY ## 1 문제 한 줄 · ## 2 페르소나 교체 |
/discover-product --update |
| ARCH의 T2 카테고리 결정(언어·런타임·프레임워크·DB·영속성·인증·배포 토폴로지) | /bootstrap-stack --migrate |
| DESIGN 시각 방향 전환(원칙·팔레트 교체) | /bootstrap-design --update |
| Charter 문제 정의 전면 재정의 | /bootstrap-project --apply |
페르소나 «문구 수정»은 foundation이 아니다 — 대상 자체가 바뀌는 교체만 해당한다. 애매하면 사용자에게 «이건 다시 발굴해야 하는 변경입니까»를 1회 묻는다.
A2. authority 판정 (ADR-060 D2 — 절차 SSOT는 그 ADR)
- 제품 의도·범위·우선순위·사용자 체감·외부 계약·데이터/보안·비용·위험 허용도·비가역 약속 →
user-choice - 스택·인증·데이터 경계·되돌리기 비싼 구조 →
user-approval - 승인된 경계 안의 가역적 내부 선택 →
agent-delegated
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.
- 8d ago First seen · 91 lines · 61 tokens per session scan A daf63d9ef51e
amend-ssot is a skill published in the GitHub repository kohj1018/agentic-dev-harness (2 stars, last pushed 11d ago), licensed MIT. It adds 61 tokens to every session and 2,675 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
sc-skill
Capture deterministic macOS screenshots for testing, docs, release notes, and marketing assets. Use when asked to automate app screenshots, batch-generate screenshot sets, standardize window sizing/composition, or choose between Peekaboo and native macOS screenshot tooling.
handover
Use when wrapping up or capturing the current state of a coding session — writes a short, dated entry to the repo's RepoHandover.md so a future agent or you can resume without grepping archived sessions. Triggers on "handover", "hand off", "write handover", "capture state", "checkpoint this session".
agent-session-format-check
Verify agent session format compatibility for Agent Sessions. Use when any agent CLI updates, when monitoring flags drift, or when bumping max verified versions (fixtures + docs + tests). Covers session schema, usage/limits tracking, storage backends, and discovery path contracts for all supported agents.
agent-support-matrix
Maintain Agent Sessions agent support matrix and JSON/JSONL parsing compatibility. Use when checking upstream agent releases for session format changes, updating max verified versions in docs/agent-support/agent-support-matrix.yml, or updating docs/agent-json-tracking.md and fixtures/tests.
do-it-architecture
Use when authority, ownership, contracts, dependency boundaries, migration, recovery, or structural deletion can change a design.
do-it-review
Use to assess requirements and implementation quality independently, or to resolve a batch of review findings.