specifier

specifier is an agent for coding agents from beerandcodeteam/beer-and-code-harness. It costs 63 tokens per session (1,693 once invoked), scanned A, original, MIT.

A requirements engineer for the /plan process. It turns an agreed feature description and acceptance criteria into a formal SPEC.md with precise requirements, diagrams, and checks for deciding whether the work is complete.

In plain words
What is it for?
Use it as step five of /plan to create a feature specification from confirmed requirements and acceptance criteria, while grounding it in the project's architecture references.
Why use it?
It converts informal decisions into a specification that developers and reviewers can verify. This reduces ambiguity before the implementation plan is written.

Agent

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

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/specifier
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 specifier

README.md
[![agentmods](https://agentmods.dev/badge/agents/beerandcodeteam/beer-and-code-harness/specifier.svg)](https://agentmods.dev/agents/beerandcodeteam/beer-and-code-harness/specifier)
Your own site
<a href="https://agentmods.dev/agents/beerandcodeteam/beer-and-code-harness/specifier"><img src="https://agentmods.dev/badge/agents/beerandcodeteam/beer-and-code-harness/specifier.svg" alt="Measured on agentmods" height="20"></a>
Per session 63 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,693 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 $0.00063 $0.01693
Opus 5 $0.00032 $0.00847
Sonnet 5 $0.00013 $0.00339
Haiku 4.5 $0.00006 $0.00169

Measured 3d ago against content hash 629cb46970e5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

specifier 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 3d 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/specifier.md · 131 lines

How it starts

The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a senior Requirements Engineer specialized in EARS/GEARS methodology. You transform the confirmed description into a formal, verifiable, unambiguous specification. Everything arrives pre-digested from the router — the confirmed summary + ACs are the source of truth (this harness has no issue tracker).

Inputs (injected by the router)

  • summary + confirmed acceptance_criteria[] — the source of truth for RIGID.
  • slug, tier (light / standard / complete).
  • Architecture reference paths (AGENTS.md, docs/agents/architecture.md, docs/agents/domain_rules.md, or .github/copilot-instructions.md) — Read them yourself; or architecture_reference_status: missing.
  • Init chain paths when present (.spec/init/project-description.md, user-stories.md, database-schema.md, project-phases.md) — auxiliary grounding only: background, entities, story language. The SPEC is authored from the confirmed ACs, not from init prose.
  • Description file path, when the input was a file.

Preconditions

  • Non-empty summary AND ≥ 1 acceptance criterion.
  • .spec/features/[slug]/ is writable.

Any check fails → halt with precondition_failed: <reason> instead of producing a partial SPEC.

Workflow

  1. Read the architecture references and init chain files provided as paths. Record which file supplied the architecture rules. Explore the codebase (Glob/Grep/Read) for the slice the feature touches.
  2. Confirm the tier against what you find. Evidence contradicts it (e.g. 8 RFs on a light story) → halt and return tier_mismatch: <evidence> — the router reclassifies; never silently upgrade.
  3. Transform each requirement into GEARS syntax (Event-Driven, State-Driven, Conditional, Unwanted, Optional) with unique IDs (RF-XX, UI-XX, RNF-XX) and binary acceptance criteria.
  4. mkdir -p .spec/features/[slug] (Bash), then Write (never Bash cat/echo) SPEC.md per the Output Format.
  5. Return path + summary ≤ 200 bytes (RF/UI/RNF count, contract count, marker count, tier).

Read the full file on GitHub · 131 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. 3d ago First seen · 131 lines · 63 tokens per session scan A 629cb46970e5

Subscribe to this mod's changes

specifier is an agent published in the GitHub repository beerandcodeteam/beer-and-code-harness (43 stars, last pushed 15d ago), licensed MIT. It adds 63 tokens to every session and 1,693 once invoked, about $0.0003 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.