What is adr-workflow?

A workflow for deciding when to write an architecture decision record, a document that explains an important technical choice.

Use it to assess ADRs, draft or update them, and lint their structure and supporting evidence.

It helps teams preserve the reasoning behind decisions and check that the record matches the issue, specifications, tests, and source code.

adr-workflow — Agent by harumiWeb

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.

agentmods

npx agentmods add agents/harumiweb/exstruct/adr-workflow

Clone the repo

git clone --depth 1 https://github.com/harumiWeb/exstruct

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,470 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

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	$0.00000	$0.01470
Opus 5	$0.00000	$0.00735
Sonnet 5	$0.00000	$0.00294
Haiku 4.5	$0.00000	$0.00147

Measured 2d ago against content hash 1ae0d299ac12, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

adr-workflow 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 2d 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.

dev-docs/agents/adr-workflow.md · 124 lines

How it starts

The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ADR workflow

This document defines the standard flow for handling ADRs from issues and PRs.

Scope of Phase 1

Phase 1 standardizes only the following:

Determining whether an ADR is needed
Drafting a new ADR or proposing an update to an existing ADR
Linting ADR documents

Additions in Phase 2

Phase 2 adds the following on top of Phase 1:

Auditing ADR consistency against specs / tests / src via adr-reconciler
Updating ADR indexes and relationship maps via adr-indexer

Additions in Phase 3

Phase 3 adds the following on top of Phase 1 + 2:

Design review of ADR drafts via adr-reviewer

Standard flow

Read the issue or PR
Read related docs/, dev-docs/specs/, dev-docs/adr/, tests/, and src/, and gather the evidence triad needed for the decision
Use adr-suggester to decide required / recommended / not-needed
Even when the verdict is not-needed, leave the rationale and evidence triad in the issue or PR
When the verdict is required or recommended, use adr-drafter to produce a new ADR draft or a proposal to update an existing ADR
Use adr-linter to check structure and evidence
If adr-linter reports unresolved high / medium findings, revise the draft and rerun step 6
Use adr-reviewer to review design soundness, conflicts with existing ADRs, and compatibility / rollout / fallback / safety impact. If the ADR touches public API / CLI / MCP, include related docs/ in scope
If adr-reviewer returns revise, revise the draft and rerun steps 6-8 as needed
If adr-reviewer returns escalate, send the issue back to the issue or PR as a point that requires human judgment
Run adr-reconciler when an ADR is newly added or updated, or when the change includes a policy-level shift
At merge time, recheck consistency with related specs / docs / tests and reconciliation findings
If an ADR was added, updated, or superseded, run adr-indexer to synchronize README.md, index.yaml, and decision-map.md

Read the full file on GitHub · 124 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.

2d ago First seen · 124 lines · 0 tokens per session scan A 1ae0d299ac12

Subscribe to this mod's changes

adr-workflow is an agent published in the GitHub repository harumiWeb/exstruct (195 stars, last pushed 2mo ago), licensed BSD-3-Clause. It costs nothing until one of its globs matches a file; then it loads 1,470 tokens. 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.

Code review Data and AI Documents LLM RAG data-ex document-ai excel structured-data

adr-workflow

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

ADR workflow

Scope of Phase 1

Additions in Phase 2

Additions in Phase 3

Standard flow

What this file has done since we first saw it

Other agents, from other repositories

ai-chat

ai-doc-bridge

licensing-billing

version-control

office-addin

sidebar-shell