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 agentmods add agents/beerandcodeteam/beer-and-code-harness/specifiergit clone --depth 1 https://github.com/beerandcodeteam/beer-and-code-harnessWrote 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/agents/beerandcodeteam/beer-and-code-harness/specifier)<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>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 | $0.00063 | $0.01693 |
| Opus 5 | $0.00032 | $0.00847 |
| Sonnet 5 | $0.00013 | $0.00339 |
| Haiku 4.5 | $0.00006 | $0.00169 |
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.
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+ confirmedacceptance_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; orarchitecture_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
summaryAND ≥ 1 acceptance criterion. .spec/features/[slug]/is writable.
Any check fails → halt with precondition_failed: <reason> instead of producing a partial SPEC.
Workflow
- 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.
- Confirm the tier against what you find. Evidence contradicts it (e.g. 8 RFs on a
lightstory) → halt and returntier_mismatch: <evidence>— the router reclassifies; never silently upgrade. - 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.
mkdir -p .spec/features/[slug](Bash), then Write (never Bash cat/echo)SPEC.mdper the Output Format.- Return path + summary ≤ 200 bytes (RF/UI/RNF count, contract count, marker count, tier).
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.
- 3d ago First seen · 131 lines · 63 tokens per session scan A 629cb46970e5
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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
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.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.