agentmods.dev

adr-ref-guard

A manual check for stale references to architecture decision records, or ADRs—documents that record important technical choices. It looks for references to decisions that have been superseded or deprecated.

In plain words
What is it for?
Use it before a pull request, after replacing an ADR, or when checking whether Markdown documentation refers to current decisions.
Why use it?
It helps catch documentation that still points to an outdated technical decision without changing the files automatically.

Skill for Claude CodeCodex

2 2d ago A scan 34 tokens original MIT
View the source file musingfox/cc-plugins
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/musingfox/cc-plugins/adr-ref-guard
Any agent
npx skills add musingfox/cc-plugins --skill adr-ref-guard
Clone the repo
git clone --depth 1 https://github.com/musingfox/cc-plugins

Made for: Claude Code, Codex.

Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 555 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 $0.00034 $0.00555
Opus 5 $0.00017 $0.00278
Sonnet 5 $0.00007 $0.00111
Haiku 4.5 $0.00003 $0.00056

Measured yesterday against content hash 780ba58cc678, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

adr-ref-guard 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 yesterday.

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.

adr/skills/adr-ref-guard/SKILL.md · 57 lines

How it starts

The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ADR Reference Guard

Check markdown files for references to superseded or deprecated ADRs. Advisory only — never auto-replace.

When to Use

This is a manual check skill — invoke it when you want to audit ADR references:

  • Before a PR review, to catch stale ADR references
  • After an ADR supersession, to find docs that reference the old ADR
  • When the user asks to verify ADR references are current

This skill does NOT auto-activate on Write/Edit operations.

Detection Patterns

Scan the content being written/edited for:

  1. ADR-NNNN or ADR NNNN (any digit count)
  2. Markdown links: [...](path/to/NNNN-*.md)
  3. Phrases: "as decided in ADR", "per ADR", "see ADR", "according to ADR", "defined in ADR"

Workflow

  1. Extract references: Identify all ADR numbers referenced in the content
  2. Locate ADR directory: Use Glob to find {docs/decisions,docs/adr,adr,decisions}/[0-9][0-9][0-9][0-9]-*.md
  3. Find ADR files: For each referenced number, Glob for NNNN-*.md in the ADR directory
  4. Check status: Read each referenced ADR file, parse YAML frontmatter status field
  5. Warn if needed:
    • If status starts with superseded by: warn with the replacement ADR
    • If status is deprecated: warn about relevance
    • If status is proposed or accepted: no warning needed

Warning Format

Present warnings after the write/edit operation completes. Include the file being edited:

ADR Reference Warning (in docs/setup.md):
- ADR-0003 (Use PostgreSQL) is superseded by ADR-0007 (Use SQLite).
  Consider updating the reference to ADR-0007.
- ADR-0005 (Legacy Auth) is deprecated.
  Verify this reference is still relevant.

Constraints

  • Never auto-replace references. Only inform the user.
  • Never block the write/edit operation. Present the warning after completion.
  • If multiple ADRs are referenced and some are current, only warn about the stale ones.
  • If multiple stale references found, suggest running ADR consistency check for a full audit.

Read the full file on GitHub · 57 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. yesterday First seen · 57 lines · 34 tokens per session scan A 780ba58cc678

Subscribe to this mod's changes

adr-ref-guard is a skill published in the GitHub repository musingfox/cc-plugins (2 stars, last pushed 2d ago), licensed MIT. It adds 34 tokens to every session and 555 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 2026-08-31.

Code reviewPlanningWriting and docs
Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens