agentleFS
ziffanziffan/auto-continue-cli-agent/.claude/skills/adr/SKILL.md

adr

Skill1 starsChanged 4 months agoApache-2.0View on GitHub

Buat, supersede, atau tinjau Architecture Decision Record (format Nygard) dan tegakkan decision discipline locked/pending/obsolete di DECISIONS.md. Gunakan saat ada keputusan struktural baru (stack, auth, multi-tenancy, deployment, data retention, model routing, batas otonomi agent), saat user atau agent lain mengusulkan mengubah keputusan yang sudah Locked (ingatkan dan minta justifikasi revisit formal), saat user tampak goyah terhadap keputusan lama, atau saat menemukan keputusan penting yang belum tercatat.

90 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use fdr, runbook and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • thiagofgfSkill

    fdr

    Use when creating, changing, reviewing, retiring, auditing, or backfilling implemented user-visible feature behavior, permissions, feature-specific rationale, tradeoffs, or relationships to architectural decisions.

    Also in 3 projects that use this

  • AnthropicSkill

    runbook

    Create or update an operational runbook for a recurring task or procedure. Use when documenting a task that on-call or ops needs to run repeatably, turning tribal knowledge into exact step-by-step commands, adding troubleshooting and rollback steps to an existing procedure, or writing escalation paths for when things go wrong.

    Also in 5 projects that use this

  • drewdrewthisSkill

    sweep

    Search for similar patterns, anti-patterns, or issues elsewhere in the codebase after a fix or feature. Use after implementing a fix to catch the same bug in other places, or proactively to audit for a known pattern.

    Also in 4 projects that use this

  • vndeeSkill

    product-spec

    Use when starting a new feature, product, or project — before any architecture or code, to define what to build and why

    Also in 3 projects that use this

  • OpenAISkill

    threat-model

    Use when Codex is already in the threat-modeling phase of a security scan, the user explicitly invokes $threat-model, or the user explicitly asks to create, update, or persist a repository threat model. Do not use as the primary trigger for full PR, commit, branch, patch, or repository scans.

    Also in 6 projects that use this

  • montymiSkill

    tech-spec

    Parse and review Technical Specification documents for completeness, consistency, and implementation readiness

    Also in 3 projects that use this

The file

Files
SKILL.md

ADR & Decision Discipline

Kenapa ini penting: agent tidak ingat sesi sebelumnya, dan sesi makin banyak. Tanpa DECISIONS.md yang ditegakkan, keputusan yang sama di-relitigasi berulang — dengan lawan debat yang selalu segar dan persuasif. File ini adalah pertahanannya.

Step 0 — Selalu cek DECISIONS.md dulu

Sebelum menulis apa pun, baca docs/DECISIONS.md (atau docs/adr/):

  • Topik sudah ada dan Locked → JANGAN buat ADR baru diam-diam. Tunjukkan keputusan lama ke user, lalu tanya: ada alasan revisit formal? Tanpa justifikasi eksplisit (fakta baru, constraint berubah, insiden), pertahankan keputusan lama dan katakan itu.
  • Topik ada dan Pending → lanjut proses memutuskan, tutup pending-nya.
  • Topik baru → lanjut Step 1.

Step 1 — Tulis ADR (format Nygard)

# ADR-{NNN}: {Judul — kalimat keputusan, bukan topik}

## Status
Proposed | Accepted | Deprecated | Superseded by ADR-{XXX}

## Context
{Situasi, constraints, forces. Fakta — versi library diverifikasi via web saat lock,
bukan dari ingatan. Sebutkan angka bila ada (biaya, latensi, limit).}

## Decision
{Satu kalimat tegas, kalimat aktif: "Kami memakai X untuk Y."}

## Consequences
{Positif DAN negatif. Konsekuensi negatif yang jujur = tanda ADR matang.}

## Alternatives Rejected
{Tiap opsi + alasan spesifik ditolak — supaya tidak diusulkan ulang oleh sesi berikutnya.}

Aturan penulisan: satu ADR = satu keputusan. Nomor urut, tidak didaur ulang. Simpan di docs/adr/ADR-NNN-{slug}.md, atau sebagai entri D-NNN di docs/DECISIONS.md untuk proyek kecil — ikuti konvensi yang sudah ada di repo.

Step 2 — Update DECISIONS.md

Tiga kategori, tegakkan tanpa kecuali:

KategoriAturan
LockedAccepted + disepakati user. Tidak di-revisit tanpa justifikasi formal. Immutable — revisi = ADR baru yang men-supersede.
PendingBelum diputuskan. WAJIB punya owner + deadline. Tanpa keduanya, entri belum sah.
ObsoleteDi-supersede. JANGAN dihapus — pindah ke Change Log dengan alasan dan pointer ke penggantinya.

Step 3 — Cek kelengkapan set minimal

Setiap proyek minimal punya ADR untuk: monolith vs services · stack utama (+ pin versi) · auth approach · multi-tenancy model · deployment · data retention · model routing policy (model/effort per jenis task + budget API per bulan) · batas otonomi agent (aksi auto vs wajib manual approval). Bila proyek menyentuh data pribadi: + lokasi data (Indonesia vs asing, dengan alasan).

Ada yang belum? Laporkan sebagai Pending + usulkan owner (biasanya user) + deadline.

Alur supersede

  1. Tulis ADR baru dengan Context yang menjelaskan kenapa keputusan lama tidak lagi tepat.
  2. Status ADR lama → Superseded by ADR-{baru}. Isi lama TIDAK diedit.
  3. Pindahkan entri lama di DECISIONS.md ke Obsolete/Change Log.
  4. Cek dampak: file docs lain yang merujuk keputusan lama (ARCHITECTURE, CONVENTIONS, MILESTONES) → update + catat di Change Log masing-masing.

Output wajib ke user

ADR lengkap + posisi barunya di DECISIONS.md + daftar dokumen lain yang ikut diubah. Bila menolak revisit: kutip keputusan Locked + tanggalnya + alasan aslinya.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.