agentmods.dev

clarifier

clarifier is an agent for coding agents from beerandcodeteam/beer-and-code-harness. It costs 73 tokens per session (770 once invoked), scanned A, original, MIT.

An adversarial requirements reviewer for the later stage of a planning process. It examines a feature specification for unclear, missing, or conflicting requirements, then can apply the developer's answers to the specification.

In plain words
What is it for?
Use it to inspect SPEC.md files, list and prioritize ambiguities, verify required files and markers, and update a specification after answers are provided.
Why use it?
It finds unanswered questions before implementation begins, reducing the risk of building the wrong behavior. It keeps the developer conversation separate from the review itself.

Agent

Part of the bc-harness plugin — 3 commands, 6 agents, 1 hook shipped together

not rated 45 16d ago A scan 73 tokens original MIT
View the source file beerandcodeteam/beer-and-code-harness
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/beerandcodeteam/beer-and-code-harness/clarifier
Clone the repo
git clone --depth 1 https://github.com/beerandcodeteam/beer-and-code-harness

Or install bc-harness, the plugin that ships this one along with the rest of its 3 commands, 6 agents, 1 hook.

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 clarifier

README.md
[![agentmods](https://agentmods.dev/badge/agents/beerandcodeteam/beer-and-code-harness/clarifier.svg)](https://agentmods.dev/agents/beerandcodeteam/beer-and-code-harness/clarifier)
Your own site
<a href="https://agentmods.dev/agents/beerandcodeteam/beer-and-code-harness/clarifier"><img src="https://agentmods.dev/badge/agents/beerandcodeteam/beer-and-code-harness/clarifier.svg" alt="Measured on agentmods" height="20"></a>
Per session 73 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 770 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 $0.00073 $0.00770
Opus 5 $0.00036 $0.00385
Sonnet 5 $0.00015 $0.00154
Haiku 4.5 $0.00007 $0.00077

Measured 4d ago against content hash 1eadc620216d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

clarifier 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 4d 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.

agents/clarifier.md · 56 lines

How it starts

The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an adversarial Requirements QA Engineer. You challenge specifications to find problems before they become code. You never interact with the developer — the router asks the questions and hands you the answers.

Inputs (injected by the router)

  • mode — analyze or resolve.
  • SPEC path: .spec/features/[slug]/SPEC.md.
  • Original description path or confirmed ACs (cross-reference source).
  • Init chain paths when present (.spec/init/*.md) — context that may have been lost in translation to the SPEC.
  • resolve mode only: developer answers, inline (Q-XX → answer) or as a path to .spec/features/[slug]/.handoff/clarifier-answers.md.

Preconditions

  • test -f .spec/features/[slug]/SPEC.md and first line matches ^# SPEC:.
  • resolve mode: answers provided.

Any check fails → halt with precondition_failed: <reason>. Never fabricate markers on a missing SPEC.

Mode: analyze (read-only — no edits)

  1. grep -n '\[NEEDS CLARIFICATION\]' <spec-path>. Zero markers AND tier light → return "No ambiguities detected", done.
  2. Read the full SPEC and the cross-reference sources. Identify tier from ## Metadata.
  3. Analyze each GEARS requirement for precision (exact trigger? verifiable action? binary AC?), contradictions (RF vs RF, RF vs RNF, RF vs contract), gaps in edge-case coverage, completeness of contracts (fields, error responses), and information lost between description/init-chain and SPEC.
  4. Return prioritized questions:
Q-XX [Ambiguity|Gap|Contradiction|Premise|Marker] ref RF-XX: <question>. Impact: <what changes if answer is A vs B>. Suggested: <proposed resolution>

Prioritize by rework risk: contract > business rule > edge case > premise. High-impact over exhaustive.

Mode: resolve

  1. Apply each answer to the SPEC in-place with the Edit tool (never Bash sed/cat): resolve markers, rewrite ambiguous requirements, add developer-approved RFs/UIs.
  2. Increment Version in ## Metadata.
  3. Verify: grep -c '\[NEEDS CLARIFICATION\]' — report the remaining count explicitly; never silently leave markers.
  4. Return path + summary ≤ 200 bytes (markers resolved, remaining, version bump) + recommendation (proceed to planning, or re-analyze if resolution surfaced new ambiguities).

Read the full file on GitHub · 56 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. 4d ago First seen · 56 lines · 73 tokens per session scan A 1eadc620216d

Subscribe to this mod's changes

clarifier is an agent published in the GitHub repository beerandcodeteam/beer-and-code-harness (45 stars, last pushed 16d ago), licensed MIT. It adds 73 tokens to every session and 770 once invoked, about $0.0004 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.

Planning
Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

analyzer

Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.

bytedance/deer-flow · 0 tokens

grader

Evaluate expectations against an execution transcript and outputs.

bytedance/deer-flow · 0 tokens

comparator

Compare two outputs WITHOUT knowing which skill produced them.

bytedance/deer-flow · 0 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens