doccraft-adr

doccraft-adr is a skill for Claude Code from alexpialetski/doccraft. It costs 108 tokens per session (2,637 once invoked), scanned A, original, MIT.

A guide for writing architecture decision records (ADRs), which are dated documents that preserve important software design decisions and their reasoning.

In plain words
What is it for?
Creating or updating decision records under docs/adr/, including their context, decision, consequences, and status.
Why use it?
It records accepted and rejected options so the team and coding agents can understand past choices without reopening settled discussions.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

Good fit Creating or updating decision records under docs/adr/, including their context, decision, consequences…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/alexpialetski/doccraft/doccraft-adr
Install

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.

Any agent
npx skills add alexpialetski/doccraft --skill doccraft-adr
Clone the repo
git clone --depth 1 https://github.com/alexpialetski/doccraft

Made for: Claude Code.

Wrote 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.

agentmods badge for doccraft-adr

README.md
[![agentmods](https://agentmods.dev/badge/skills/alexpialetski/doccraft/doccraft-adr.svg)](https://agentmods.dev/skills/alexpialetski/doccraft/doccraft-adr)
Your own site
<a href="https://agentmods.dev/skills/alexpialetski/doccraft/doccraft-adr"><img src="https://agentmods.dev/badge/skills/alexpialetski/doccraft/doccraft-adr.svg" alt="Measured on agentmods" height="20"></a>
Per session 108 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,637 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00108 $0.02637
Opus 5 $0.00054 $0.01319
Sonnet 5 $0.00022 $0.00527
Haiku 4.5 $0.00011 $0.00264

Measured 6d ago against content hash d0f93e67330b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

doccraft-adr 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 6d 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.

.claude/skills/doccraft-adr/SKILL.md · 263 lines

How it starts

The opening of the file, as written. The whole thing — 263 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Managed by doccraftdoccraft update regenerates this file. Local edits will be overwritten. See doccraft.json to override project-specific vocabulary and paths without touching this file.

doccraft — architecture decision records (ADRs)

When to use

  • A chat or design exploration reached a conclusion worth keeping (yes, no, defer, or "use X instead of Y").
  • You need to supersede an older ADR without rewriting history.
  • A rejected option should stay visible so the team does not revisit the same dead end.

Not every brainstorm needs an ADR — only decisions you want git history and agents to reuse.

YAML frontmatter

Use valid YAML between --- delimiters at the top of the file, or an inline **Status:** line immediately after the title. If the project sets adr.require_frontmatter: true in doccraft.yaml, frontmatter is mandatory — otherwise either form is acceptable, but frontmatter is preferred for machine-readability.

Field Required Values / notes
adr yes Three-digit zero-padded string matching the filename number (e.g. "007"). MUST be unique — verify before writing.
status yes One of the values in adr.status config (default: Proposed | Accepted | Superseded by NNN-slug | Deprecated). If the user does not specify, default to Proposed.
updated yes ISO date YYYY-MM-DD. MUST be set on creation and updated on every meaningful edit.
supersedes optional YAML list of ADR filenames this record supersedes (e.g. [005-old-approach.md]). Omit or [] if none.
superseded_by optional Filename of the ADR that replaced this one. Set to null or omit when active.

Do not invent new values for status without first adding them to the adr.status list in doccraft.yaml — that is the single source of truth. One-off nuance belongs in the body, not as a new enum value.

File location and naming

  • Path: docs/adr/NNN-short-slug.md — three-digit zero-padded index, kebab-case slug (e.g. 001-managed-postgres.md).
  • docs/adr/README.md is the index — do NOT treat it as an ADR; no NNN- prefix, no required Nygard sections.
  • Pick the next unused number. NEVER renumber published ADRs; add a new ADR that supersedes instead.

Read the full file on GitHub · 263 lines

Changes

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.

  1. 6d ago First seen · 263 lines · 108 tokens per session scan A d0f93e67330b

Subscribe to this mod's changes

doccraft-adr is a skill published in the GitHub repository alexpialetski/doccraft (4 stars, last pushed 3mo ago), licensed MIT. It adds 108 tokens to every session and 2,637 once invoked, about $0.0005 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.

Related

Other skills, from other repositories

comprehensive-enrichment

Enrich any person or company from any identifier — email, name, LinkedIn URL, domain, company name, Twitter/X handle. Use when asked to enrich, look up, or research a lead, contact, person, or company.

gooseworks-ai/goose-skills · 53 tokens

create-workflow-diagram

Create FigJam/Miro-style workflow diagrams as high-quality PNG images from plain-text workflow descriptions. Renders beautiful HTML diagrams with connected nodes, arrows, and labels, then screenshots them for sharing.

gooseworks-ai/goose-skills · 45 tokens

data-charts-tako

Search and visualize the world's data - get charts, insights, and embeddable knowledge cards for finance, economics, demographics, sports, and more.

gooseworks-ai/goose-skills · 35 tokens

lead-discovery

Orchestrator that runs first for lead generation requests. Gathers business context via website analysis or questions, identifies competitors, builds ICP, and routes to signal skills with pre-filled inputs.

gooseworks-ai/goose-skills · 41 tokens

email-finder-hunter

Email finder and verifier - find emails, verify deliverability, discover companies.

gooseworks-ai/goose-skills · 20 tokens

meta-ad-scraper

Scrape competitor ads from Meta's Ad Library (Facebook, Instagram, Messenger, Threads, WhatsApp). Search by company name, Facebook Page URL, or keyword. Returns ad creatives, spend estimates, reach, impressions, and campaign details. Use for competitive ad research, messaging analysis, and creative inspiration.

gooseworks-ai/goose-skills · 67 tokens