guardian

guardian is a skill for Claude Code from rvdbreemen/adr-kit. It costs 23 tokens per session (209 once invoked), scanned A, original, MIT.

A project-health skill for ADRs, or Architecture Decision Records—short documents that explain important software design choices.

In plain words
What is it for?
Use it to run local ADR checks, review proposed decisions, and report project drift or failed retrieval checks.
Why use it?
It helps find outdated decisions, differences between decisions and the code, and problems retrieving decision information.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions Codex; $skill-name invocation.

Part of the adr-kit plugin — 17 skills, 1 command, 1 agent, 6 hooks, 1 MCP server shipped together

Good fit Use it to run local ADR checks, review proposed decisions, and report project drift or failed retrieval checks.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/rvdbreemen/adr-kit/guardian
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.

Any agent
npx skills add rvdbreemen/adr-kit --skill guardian
Clone the repo
git clone --depth 1 https://github.com/rvdbreemen/adr-kit

Made for: Claude Code.

Or install adr-kit, the plugin that ships this one along with the rest of its 17 skills, 1 command, 1 agent, 6 hooks, 1 MCP server.

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.

agentmods badge for guardian

README.md
[![agentmods](https://agentmods.dev/badge/skills/rvdbreemen/adr-kit/guardian/github.svg)](https://agentmods.dev/skills/rvdbreemen/adr-kit/guardian)
Your own site
<a href="https://agentmods.dev/skills/rvdbreemen/adr-kit/guardian"><img src="https://agentmods.dev/badge/skills/rvdbreemen/adr-kit/guardian/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.

agentmods 80×15 button for guardian

Your own site · 80×15
<a href="https://agentmods.dev/skills/rvdbreemen/adr-kit/guardian"><img src="https://agentmods.dev/badge/skills/rvdbreemen/adr-kit/guardian.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 23 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 209 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00023 $0.00209
Opus 5 $0.00012 $0.00105
Sonnet 5 $0.00005 $0.00042
Haiku 4.5 $0.00002 $0.00021

Measured 9d ago against content hash 461046ac8d6d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

guardian 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 9d 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.

codex/skills/guardian/SKILL.md · 19 lines

What it actually says

ADR guardian

Invoke explicitly with $adr-kit:guardian when needed. Resolve <plugin-root> from this installed skill. Use only bundled, local ADR Kit tools and follow this canonical workflow:

  1. Run adr-doctor, adr-retire, adr-status, and adr-guardian retrieval-health against the active workspace and report drift or failed retrieval probes first.
  2. Rank Proposed ADRs by active implementation link, shipped-but-Proposed, ready-for-confirmation, open human questions, age, and lowest quality; show at most three client-native grill invocations.
  3. Use local-model judgment automatically when configured; require explicit opt-in before a paid or cloud model.

Do not contact another model or mutate user-owned instructions.

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. 9d ago First seen · 19 lines · 23 tokens per session scan A 461046ac8d6d

Subscribe to this mod's changes

guardian is a skill published in the GitHub repository rvdbreemen/adr-kit (8 stars, last pushed yesterday), licensed MIT. It adds 23 tokens to every session and 209 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

audit

Audit a documentation-led repo against its own conventions — contiguous ADR numbering, INDEX sync, plan/ coverage, required sections, status validity, cross-reference resolution, language mandate, ADR-privacy leaks into user-visible code, cross-worktree collisions (duplicate numbers, duplicate plan ownership, same ADR…

EvolveHQ/docflow · 141 tokens

adr-compliance

This skill should be used when the user asks about "ADR compliance", "architecture compliance", "ADR audit", "enforce ADRs", "check code against ADRs", "ADR violations", or needs guidance on auditing code compliance with accepted architectural decision records.

zircote-plugins/adr · 56 tokens

openlore-execute-refactor

Apply a confirmed .openlore/refactor-plan.md with a test gate after each change. Use when asked to execute or continue an OpenLore refactoring plan.

clay-good/OpenLore · 41 tokens

michel-packmind-engineer-review

Review an implemented GitHub issue the way a senior Packmind engineer would — the human-judgment checks that ESLint, the TypeScript compiler, and e2e tests cannot catch (authorization scoping, hexagonal-architecture conformance, analytics-event wiring, UX copy, UI reactivity, CLI behavior, multi-tenancy safety, and…

PackmindHub/packmind · 181 tokens

idea-team

A structured group discussion for exploring a product idea through three roles: researcher, critic, and analogy finder. The roles look for evidence, weaknesses, and useful comparisons.

majiayu000/spellbook · 182 tokens

codex-agent

Use when you want a second-opinion review via Codex CLI, cross-verification after another agent implements changes, debugging help, or alternative implementation proposals. Requires Codex CLI to be installed and authenticated.

majiayu000/spellbook · 45 tokens