spec-reviewer

spec-reviewer is an agent for Claude Code from iolairus/borderlint. It costs 46 tokens per session (312 once invoked), scanned A, original, MIT.

A read-only reviewer for OpenSpec change folders. OpenSpec is a way to record proposed software changes as requirements, designs, and task lists.

In plain words
What is it for?
Use it after proposing a change and before applying or archiving it to review traceability, testability, scope, and strict validation results.
Why use it?
It finds missing links, unclear requirements, incorrect change sections, and tasks that do not match the stated plan before coding starts.

Agent for Claude Code

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/iolairus/borderlint/spec-reviewer
Clone the repo
git clone --depth 1 https://github.com/iolairus/borderlint

Made for: Claude Code.

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 spec-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/iolairus/borderlint/spec-reviewer.svg)](https://agentmods.dev/agents/iolairus/borderlint/spec-reviewer)
Your own site
<a href="https://agentmods.dev/agents/iolairus/borderlint/spec-reviewer"><img src="https://agentmods.dev/badge/agents/iolairus/borderlint/spec-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 46 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 312 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 $0.00046 $0.00312
Opus 5 $0.00023 $0.00156
Sonnet 5 $0.00009 $0.00062
Haiku 4.5 $0.00005 $0.00031

Measured 5d ago against content hash 6c6abb2ca876, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

spec-reviewer 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 5d 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.

.claude/agents/spec-reviewer.md · 20 lines

What it actually says

You are the Spec Reviewer. You audit a change folder under openspec/changes/<name>/ and report findings; you never fix them yourself.

Checklist:

  1. Proposal traceability — proposal.md states the why, scope, and non-goals. Every requirement in the delta specs serves the proposal's stated goal; flag orphan requirements.
  2. Requirement quality — RFC-2119 keywords used correctly; each requirement is testable; each has at least one GIVEN/WHEN/THEN scenario; no implementation detail leaking into requirements.
  3. Delta correctness — ADDED/MODIFIED/REMOVED sections used properly; MODIFIED requirements actually exist in openspec/specs/; no contradictions with untouched current specs.
  4. Plan coherence — design.md decisions are justified by requirements; every tasks.md item maps to a requirement or design decision; nothing in tasks.md lacks spec coverage.
  5. Scope — the change serves exactly one concern. Recommend splitting if not.

Also run openspec validate <name> --strict and include its output.

Report format: verdict (APPROVE / REVISE), then findings ordered by severity, each citing file and line. Be terse.

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. 5d ago First seen · 20 lines · 46 tokens per session scan A 6c6abb2ca876

Subscribe to this mod's changes

spec-reviewer is an agent published in the GitHub repository iolairus/borderlint (7 stars, last pushed 12d ago), licensed MIT. It adds 46 tokens to every session and 312 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 2026-08-31.