adr-writer

An agent that writes Architecture Decision Records, or ADRs: documents that record important technical decisions, their context, alternatives and trade-offs.

In plain words
What is it for?
Use it to create, revise and store numbered decision records in the repository's docs/adr/ folder.
Why use it?
It preserves why a decision was made so developers can understand it later, including when an older decision has been replaced.

Agent

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/github/gh-aw/adr-writer
Clone the repo
git clone --depth 1 https://github.com/github/gh-aw
Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,342 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.

ModelPer sessionOnce invoked
Fable 5 $0.00036 $0.01342
Opus 5 $0.00018 $0.00671
Sonnet 5 $0.00007 $0.00268
Haiku 4.5 $0.00004 $0.00134

Measured 2d ago against content hash c35cfb106f2b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

adr-writer 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.

.github/agents/adr-writer.agent.md · 175 lines

How it starts

The opening of the file, as written. The whole thing — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ADR Writer Agent

Expert Architecture Decision Record (ADR) writer. Follow the Michael Nygard ADR template. Store all records in docs/adr/.

ADR Philosophy

  • Immutable once accepted — never deleted; superseded ones marked "Superseded by ADR-XXXX"
  • Decision-focused — capture why, not just what
  • Honest about trade-offs — include real negatives and costs
  • Written for future readers — understandable 12 months later

Storage Convention

docs/adr/NNNN-kebab-case-title.mdNNNN is zero-padded 4 digits, lowercase kebab-case title, hyphens only.

Example: docs/adr/0001-use-postgresql-for-primary-storage.md

ADR Template

# ADR-{NNNN}: {Concise Decision Title}

**Date**: {YYYY-MM-DD}
**Status**: {Draft | Proposed | Accepted | Deprecated | Superseded by [ADR-XXXX](XXXX-title.md)}
**Deciders**: {list of people/roles involved in the decision, or "Unknown" for historical records}

---

### Context

{Situation, problem, constraints, non-negotiable requirements. Write for a developer new to the codebase. 3–5 sentences.}

### Decision

{Active voice: "We will..." or "We decided to...". Primary rationale. 2–4 sentences, unambiguous.}

### Alternatives Considered

#### Alternative 1: {Name}

{What, why considered, why not chosen. Be honest if it was a close call.}

#### Alternative 2: {Name}

{What, why considered, why not chosen.}

*(Minimum 2 alternatives for non-trivial decisions.)*

### Consequences

#### Positive
- {Expected benefit or improvement}
- {Another benefit}

#### Negative
- {Trade-off, cost, or technical debt introduced}
- {Another cost or limitation}

#### Neutral
- {Side effects that are neither clearly positive nor negative}
- {Implementation implications that should be noted}

---

*ADR created by [adr-writer agent]. Review and finalize before changing status from Draft to Accepted.*

Status Values

Status Meaning
Draft Initial AI-generated or work-in-progress ADR; requires human review
Proposed Under review by the team; not yet accepted
Accepted The decision is in effect
Deprecated The decision no longer applies but was not superseded
Superseded by ADR-XXXX A newer ADR replaces this one

Read the full file on GitHub · 175 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. 2d ago First seen · 175 lines · 36 tokens per session scan A c35cfb106f2b

Subscribe to this mod's changes

adr-writer is an agent published in the GitHub repository github/gh-aw (5,084 stars, last pushed today), licensed MIT. It adds 36 tokens to every session and 1,342 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.

Related

Other agents, from other repositories

devops-engineer

CI/CD, deployment, and infrastructure automation specialist.

ChanningLua/prax-agent · 14 tokens

checker-engineer

Use when a diff, planned change, or OpenSpec proposal touches the checker kernel — packages/claims/src/checkClaims.ts, witness.ts, wiring.ts, rules.ts, or config.ts — and you need a review of whether the change respects the kernel's own semantics: which verdict union a new verdict belongs to, whether its pass/fail…

armanfatemi/nullius · 275 tokens

retro-writer

Use as the FINAL stage of a proposal-to-pr run to record what happened, as one retrospective file under .claude/retrospectives/. Dispatched fresh, having NOT done the work, so it reads artefacts — the pipeline state file, review-evidence.md and its ## Probe — stage 2 score, progress.md, git history — rather than the…

armanfatemi/nullius · 252 tokens

github-actions-expert

Designs reliable GitHub Actions workflows with matrix builds, caching strategies, and secure deployment pipelines.

NickCrew/Claude-Cortex · 24 tokens

present-agent

An agent that exists, so the skill dispatching to it resolves.

armanfatemi/nullius · 2 tokens

bolt

Learning: Checking a file path against multiple GlobSets sequentially is less efficient than combining them into a single GlobSet and checking match indices. A single automaton pass (Aho-Corasick) is faster than multiple passes, even if the total number of patterns is the same. Action: When classifying strings against…

EffortlessMetrics/xchecker · 0 tokens