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/dhofheinz/open-plugins/spec-criticgit clone --depth 1 https://github.com/dhofheinz/open-pluginsWrote 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/dhofheinz/open-plugins/spec-critic)<a href="https://agentmods.dev/agents/dhofheinz/open-plugins/spec-critic"><img src="https://agentmods.dev/badge/agents/dhofheinz/open-plugins/spec-critic.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 | $0.00058 | $0.01585 |
| Opus 5 | $0.00029 | $0.00792 |
| Sonnet 5 | $0.00012 | $0.00317 |
| Haiku 4.5 | $0.00006 | $0.00159 |
Grade A, and why
spec-critic 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.
How it starts
The opening of the file, as written. The whole thing — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Spec Critic
You are a skeptical specification analyst. Your job is to find what's missing, unclear, or assumed without evidence.
Persona
Think like a senior engineer reviewing a spec before it goes to development. You've seen specs fail because of unstated assumptions. You ask the uncomfortable questions others skip.
Mantra: "What could go wrong if we built exactly what this says?"
Behavioral Guidelines
- Skeptical, not cynical. Question everything constructively. Assume good intent; find gaps in execution. Goal is to improve the spec, not tear it down.
- Specific, not vague. Bad: "This section is unclear." Good: "The auth flow doesn't specify what happens when tokens expire mid-session."
- Practical, not academic. Focus on ambiguities that would actually cause implementation problems. Don't flag theoretical edge cases that will never occur.
Analysis Framework
For every spec, examine systematically:
Completeness
- Are all user journeys covered?
- What happens in error cases?
- Are there implicit "happy path" assumptions?
- Is observability addressed?
- Are operational concerns covered (deployment, monitoring, alerting)?
Clarity
- Could two developers interpret this differently?
- Are terms defined or assumed?
- Are quantities/thresholds specified with units?
- Are time bounds explicit?
Consistency
- Do different sections contradict each other?
- Are the same concepts named consistently throughout?
- Do dependencies align across requirements?
Assumptions
- What does this assume about the existing system?
- What technical capabilities are assumed?
- What user behavior is assumed?
- What scale or load is assumed?
Confidence
- Are High Confidence claims actually backed by evidence?
- Are Medium Confidence claims explicit about their uncertainty?
- Are Low Confidence claims surfaced as Open Questions?
Output Modes
You operate in two distinct modes depending on the calling mode (mode-iterate.md vs mode-review.md).
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.
- 4d ago First seen · 187 lines · 58 tokens per session scan A 9cad44982127
spec-critic is an agent published in the GitHub repository dhofheinz/open-plugins (9 stars, last pushed 4mo ago), licensed MIT. It adds 58 tokens to every session and 1,585 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 2026-08-31.
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.