adr-context

A read-only tool that loads relevant ADRs, or Architecture Decision Records, from a project's docs/adr/ folder. It filters them by the current task and summarizes the decisions and constraints that apply.

In plain words
What is it for?
Use it before building or verifying a task to find accepted decisions related to the task's topic.
Why use it?
It prevents implementation work from overlooking earlier architectural choices.

Skill for Claude CodeCodex

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 skills/qgolem/orc/adr-context
Any agent
npx skills add qGolem/orc --skill adr-context
Clone the repo
git clone --depth 1 https://github.com/qGolem/orc

Made for: Claude Code, Codex.

Per session 14 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 569 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 $0.00014 $0.00569
Opus 5 $0.00007 $0.00284
Sonnet 5 $0.00003 $0.00114
Haiku 4.5 $0.00001 $0.00057

Measured 2d ago against content hash 634315d51954, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

adr-context 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.

skills/adr-context/SKILL.md · 76 lines

How it starts

The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ADR Context Loader

Load relevant architectural decisions from docs/adr/ before implementing or verifying tasks.

Process

  1. List all ADRsGlob docs/adr/**/*.md
  2. Extract metadata — Read title (# ADR-XXX: ...) and status line from each file
  3. Filter by topic — Identify ADRs relevant to the caller's task topic (passed as $ARGUMENTS)
  4. Load relevant ADRs — Read full content of matching ADRs
  5. Output summary — Report which ADRs apply, their decisions, and constraints to respect

Implementation Steps

Step 1: Discover all ADRs

Glob pattern: docs/adr/**/*.md

Step 2: Read metadata

For each ADR file:

  • Read the first line containing # ADR-XXX: to extract title
  • Read the ## Status section to determine status (Accepted, Rejected, Superseded, etc.)

Step 3: Filter by relevance

Given the task topic from $ARGUMENTS, identify ADRs that match by:

  • Title keywords (e.g., "auth" matches "Authentication system architecture")
  • Filename patterns (e.g., ADR-001-*.md)
  • Status (only include Accepted or superseded-but-still-relevant ones)

Step 4: Load and return content

For each relevant ADR:

  • Read the full file
  • Include in output summary

Step 5: Output summary format

## Relevant ADRs for [task topic]

### ADR-XXX: [Title]
- **Status**: [Accepted/Superseded]
- **Key Decision**: [one-liner]
- **Constraints to respect**:
  - Constraint 1
  - Constraint 2
- **Full decision context**: [excerpt or link]

---

### Constraints Summary
- [List all constraints from all ADRs]

Example

If task topic is "auth", and docs/adr/ contains:

  • ADR-001-authentication-strategy.md → MATCH
  • ADR-002-database-schema.md → no match
  • ADR-003-oauth-provider-selection.md → MATCH

Output would include ADR-001 and ADR-003 with their decisions and constraints.

Output to Caller

Return the summary to the caller's context so they can see:

  • Which ADRs apply to their task
  • What architectural decisions have been made
  • What constraints must be respected during implementation/verification

Read the full file on GitHub · 76 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 · 76 lines · 14 tokens per session scan A 634315d51954

Subscribe to this mod's changes

adr-context is a skill published in the GitHub repository qGolem/orc (5 stars, last pushed 5mo ago), licensed MIT. It adds 14 tokens to every session and 569 once invoked, about $0.0001 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

foundry-config-setup

Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.

microsoft/agent-framework · 65 tokens

reflect

Review recent work, find repeated workflow patterns, and suggest reusable skills, agents, commands, config changes, or playbooks. Use when the user asks to learn from past sessions, improve recurring workflows, or identify what should be turned into reusable agent instructions.

alvinunreal/oh-my-opencode-slim · 53 tokens

codemap

Generate comprehensive hierarchical codemaps for UNFAMILIAR repositories. Expensive operation - only use when explicitly asked for codebase documentation or initial repository mapping.

alvinunreal/oh-my-opencode-slim · 34 tokens

atmos-auth

Authentication and identity management: providers (SSO/SAML/OIDC/GCP/Atmos Pro), identities, keyring, identity chaining, login/exec/shell/console, and github/sts for private GitHub access.

cloudposse/atmos · 48 tokens

workflow-init

Install and configure Vercel Workflow SDK before it exists in nodemodules. Use when the user asks to "install workflow", "set up workflow", "add durable workflows", "configure workflow sdk", or "init workflow" for Next.js, Express, Hono, Fastify, NestJS, Nitro, Nuxt, Astro, SvelteKit, or Vite.

vercel/workflow · 78 tokens

recipe-quality-profile

Proposes repository-specific quality policy for implementation and review and, after confirmation, creates or updates docs/project-context/quality.yaml. Use when asked to create or update a repository quality profile.

shinpr/claude-code-workflows · 41 tokens