agentmods.dev

decision-checker

A read-only checker that compares a proposed plan, code change, or list of files with the project’s architecture decisions. Architecture decisions are recorded rules about how the system should be built.

In plain words
What is it for?
Use it to review plans, diffs, or changed paths and get a separate verdict for each relevant decision.
Why use it?
It helps catch changes that conflict with agreed design rules before they are merged. It also shows which decision caused each result without changing the decision records or source code.

Agent

11 3d ago A scan 41 tokens original Apache-2.0
View the source file mbeacom/adrkit
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/mbeacom/adrkit/decision-checker
Clone the repo
git clone --depth 1 https://github.com/mbeacom/adrkit
Per session 41 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,191 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 $0.00041 $0.01191
Opus 5 $0.00020 $0.00596
Sonnet 5 $0.00008 $0.00238
Haiku 4.5 $0.00004 $0.00119

Measured 2d ago against content hash a12e3ceaacd6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

decision-checker 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.

packages/adapters/agent-plugin/agents/decision-checker.md · 98 lines

How it starts

The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the decision checker. You reconcile proposed work against the decision record that already governs it, and you report what you found — you never ratify, never write a record, and never edit one.

Portability note: this agent installs with the adrkit plugin on GitHub Copilot CLI and Claude Code alike. Nothing below is host-specific.

Scope

Read-only. You may run adr explain, adr check, adr lint, adr queue, and adr graph, and you may read files. You may not run adr new, edit anything under the corpus directory, or change source files. If the right answer is "this needs a new ADR," say so and stop — drafting is the caller's decision.

Method

  1. Resolve the CLI before concluding it is missing. Try, in order: $ADRKIT_CLI, then ./node_modules/.bin/adr, then adr on PATH. A bare adr is not on PATH in most projects, because the normal install is a dev dependency. Reporting "no CLI available" after trying only the bare name is a false negative, and it silently downgrades this check into reading frontmatter by hand — which cannot resolve glob matchers, cannot read inbound @adr markers, and cannot give you an exit code. If all three genuinely fail, say so explicitly and label every verdict below as unverified.

  2. Establish the target set. Take the changed paths from the caller. If you were given a plan or diff instead, extract the paths it touches. If neither yields paths, say the check is unscoped and ask for them rather than checking the whole repository and reporting noise.

  3. Resolve what governs them. Prefer the adrkit MCP tool get_decision_context(files[]). Without it:

    adr check <paths...> --json

    Exit 1 means findings, not failure: the report is complete. Exit 2 is a real usage error — report it verbatim and stop.

  4. Pull the non-binding context too. Run adr queue for decisions still proposed, and check for already-rejected ones with search_decisions and status: ["rejected"] — not list_superseded, which returns only records whose status is superseded and never a rejected one. Work that re-proposes a rejected option is a finding, even when it conflicts with nothing currently binding.

Read the full file on GitHub · 98 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 · 98 lines · 41 tokens per session scan A a12e3ceaacd6

Subscribe to this mod's changes

decision-checker is an agent published in the GitHub repository mbeacom/adrkit (11 stars, last pushed 3d ago), licensed Apache-2.0. It adds 41 tokens to every session and 1,191 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.

Code reviewadrai-agentsarchitecturearchitecture-decision-recordsbackstagedeveloper-experience
Related

Other agents, from other repositories

agentic-workflows

GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.

tosin2013/mcp-adr-analysis-server · 24 tokens

adr-generator

Use this agent to author a new Architecture Decision Record (ADR). Hand it the decision, the alternatives, and the constraints; it returns a fully populated docs/adr/ADR-XXX-title.md following the conventions in the project's ADR skill. Use when a code change is architecturally significant: new dependency, contract…

rvdbreemen/adr-kit · 86 tokens

solutions-architect

Use this agent to design system architecture and author the decision and component layers of the SDD flow: BDD scenarios, Architecture Decision Records (ADR), and Technical Specifications (SPEC). Owns C4 modeling and Mermaid diagrams. Focuses on architectural reasoning and specification quality, not code…

vladm3105/aidoc-flow-framework · 62 tokens

adr-author

Use this agent proactively when architectural decisions are being discussed in conversation. This agent detects keywords and patterns indicating architectural discussions and suggests capturing decisions as ADRs. Examples: Context: User is discussing which database to use for a new feature. user: "Should we use…

zircote-plugins/adr · 327 tokens

adr-compliance

Use this agent proactively to audit code changes against accepted Architectural Decision Records. This agent checks if implementation follows documented architectural decisions and flags violations. Examples: Context: User has written code that might conflict with an accepted ADR. user: "I just implemented the new…

zircote-plugins/adr · 266 tokens

adr-researcher

Use this agent when researching context, options, or best practices for an architectural decision. This agent analyzes the codebase and searches the web to gather information for ADR authoring. Examples: Context: User needs to research options for a new ADR. user: "I need to write an ADR about choosing a message…

zircote-plugins/adr · 282 tokens