A project-level Architecture Decision Record (ADR) file manager. It creates, updates, or replaces MADR-format files that document important technical decisions, and prepares their catalogue entry.

Use it to create a new project decision, amend an existing one, or mark an old decision as superseded, with the file path, catalogue row, and changed files returned.

It keeps decision files consistent and prevents different workflows from changing them in conflicting ways. It also records each change in the ADR catalogue.

ADRAuthor — Agent for Claude Code by attilaszasz

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.

Clone the repo

git clone --depth 1 https://github.com/attilaszasz/sdd-pilot

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/attilaszasz/sdd-pilot/_adr-author/github.svg)](https://agentmods.dev/agents/attilaszasz/sdd-pilot/_adr-author)

Your own site

<a href="https://agentmods.dev/agents/attilaszasz/sdd-pilot/_adr-author"><img src="https://agentmods.dev/badge/agents/attilaszasz/sdd-pilot/_adr-author/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/attilaszasz/sdd-pilot/_adr-author"><img src="https://agentmods.dev/badge/agents/attilaszasz/sdd-pilot/_adr-author.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 30 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,646 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.

Model	Per session	Once invoked
Fable 5.1	$0.00030	$0.01646
Opus 5	$0.00015	$0.00823
Sonnet 5	$0.00006	$0.00329
Haiku 4.5	$0.00003	$0.00165

Measured 10d ago against content hash 92336aa665ce, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

ADRAuthor 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 10d 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.

.github/agents/_adr-author.md · 140 lines

How it starts

The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Task

Execute ADR file creation, amendment, or supersession using the shared MADR authoring contract, and produce the corresponding sad.md catalog row payload.

Inputs

Fully resolved decision payload from an orchestrating workflow (system-design, plan-feature, or amend-project).

Execution Rules

All ADR file mutations in the repository flow through this subagent. No other workflow may write standalone ADR files directly. Feature-local AD-### decisions must not be routed here.

Output Format

Return a deterministic result payload with ADR ID, file path, catalog row, and changed-file list.

Operation: create | amend | supersede
DecisionScope: must be project-level (refuse otherwise)
DecisionTitle: final human-readable title
DecisionSummary: one-sentence chosen outcome
Context: structured context text (problem, forces, constraints)
DecisionDrivers: ordered list of criteria
Options: list of option objects, each with label, summary, pros, cons
ChosenOption: exact option label from the Options list
Consequences: object with positive[], negative[], and optional neutral[] bullets
Status: proposed | accepted | deprecated | superseded
Date: ISO date (YYYY-MM-DD)
Tags: list (may be empty)
RelatedArtifacts: list of traceability references (PRD capabilities, feature dirs, plan AD IDs, epic IDs)
Supersedes: required for supersede, list of ADR IDs being replaced; otherwise empty
ExistingAdrPath: required for amend, optional otherwise
TargetDir: specs/adrs/
SadPath: canonical technical-context document path (normally specs/sad.md)
ExistingAdrInventory: current ADR file list or enough context to derive it

Optional inputs:

Deciders, Consulted, Informed, ReviewDate
ExternalLinks: standards, docs, issue links
NumberHint: optional next-number hint from caller (still validated by this subagent)

Read the full file on GitHub · 140 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.

10d ago First seen · 140 lines · 30 tokens per session scan A 92336aa665ce

Subscribe to this mod's changes

ADRAuthor is an agent published in the GitHub repository attilaszasz/sdd-pilot (95 stars, last pushed 4d ago), licensed MIT. It adds 30 tokens to every session and 1,646 once invoked, about $0.0002 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 2026-08-30.

Planning Writing and docs copilot-coding-agent developer-tools github-copilot spec-driven spec-driven-development spec-kit

Spec-Driven

Use this planner when the user wants implementation to be specified and approved before code changes. Select the brief lane by default for bounded work or the full requirements -> design -> tasks lifecycle for high-risk work. Never implement before the selected lane's approval gate.

lindoelio/spec-driven-steroids · 54 tokens

sharp-edges-analyzer

Evaluates APIs, configurations, and library interfaces for misuse resistance and footgun potential. Use when reviewing code for error-prone designs, dangerous defaults, or APIs that make security mistakes easy.

stefaniuk/loadout · 44 tokens

sdd-scout

Architecture scout used only by /sdd-architecture-scan. Analyzes one worklist unit and writes its report to .sdd-scan/reports/. Not for general tasks.

GregorBiswanger/featherspec · 43 tokens

angular-implementer

Phase 4 (green/refactor/simplify) — minimum Angular production code to pass the failing test, then refactor without behavior change, then apply clarity-over-cleverness.

loiane/specs-driven-development-spring-angular · 42 tokens

angular-architect

Phase 3 — design the Angular feature, decompose into TDD-shaped frontend tasks, write ADRs. Use when the user asks for design, plan, or runs /plan for a feature touching the Angular UI.

loiane/specs-driven-development-spring-angular · 48 tokens

ndv-signal

Metrics skeptic. Use when reviewing engineering KPIs, OKRs, sprint velocity, test coverage targets, DORA metrics, or any measurement system. Audits whether metrics measure what they claim to measure. Goodhart's Law as a cognitive style — the moment a measure becomes a target, it stops being a measure, and Signal…

emb715/neurodiveragents · 76 tokens