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.
npx skills add rvdbreemen/adr-kit --skill judgegit clone --depth 1 https://github.com/rvdbreemen/adr-kitWrote 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.
[](https://agentmods.dev/skills/rvdbreemen/adr-kit/judge)<a href="https://agentmods.dev/skills/rvdbreemen/adr-kit/judge"><img src="https://agentmods.dev/badge/skills/rvdbreemen/adr-kit/judge/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.
<a href="https://agentmods.dev/skills/rvdbreemen/adr-kit/judge"><img src="https://agentmods.dev/badge/skills/rvdbreemen/adr-kit/judge.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 5.1 | $0.00022 | $0.00339 |
| Opus 5 | $0.00011 | $0.00169 |
| Sonnet 5 | $0.00004 | $0.00068 |
| Haiku 4.5 | $0.00002 | $0.00034 |
Grade A, and why
judge 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 10d 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.
What it actually says
Judge a staged diff
Invoke explicitly with $adr-kit:judge when needed.
Resolve <plugin-root> from this installed skill. Use only bundled,
local ADR Kit tools and follow this canonical workflow:
- Read the staged diff and stop clearly when it is empty.
- Call
adr-kit.adr_judge; for each violation offer supersession, a narrow new decision, or the smallest compliant code change. - When the diff implements a linked Proposed ADR or exposes an undocumented consequential decision, offer the exact client-native grill invocation without weakening Accepted ADR enforcement.
- Evaluate
llm_judge: truerules in the active session and never send code to another provider without permission. - On a settings request, run
python <plugin-root>/bin/adr-judge --adr-dir docs/adr --show-configand report every value with its provenance, including anavailable: falsebackend rather than summarizing it away. - Change the judge backend only through
adr-judge --set-backend host --host-client <this client's id>(the host model is the only backend, ADR-036); never hand-edit .adr-kit.json, never ask for an API key, and never write a credential to a file, because that file is committed and the judge refuses a key found in it.
Do not contact another model or mutate user-owned instructions.
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.
- 10d ago First seen · 22 lines · 22 tokens per session scan A 58df08d19070
judge is a skill published in the GitHub repository rvdbreemen/adr-kit (8 stars, last pushed 2d ago), licensed MIT. It adds 22 tokens to every session and 339 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.
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…
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.
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.
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…
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.
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.