Borrowing it
Nothing to install: this file belongs to ddebixx/frontend-template. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/ddebixx/frontend-template/main/.cursor/agents/spec-critic.mdgit clone --depth 1 https://github.com/ddebixx/frontend-templateWrote 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/ddebixx/frontend-template/spec-critic)<a href="https://agentmods.dev/agents/ddebixx/frontend-template/spec-critic"><img src="https://agentmods.dev/badge/agents/ddebixx/frontend-template/spec-critic/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/ddebixx/frontend-template/spec-critic"><img src="https://agentmods.dev/badge/agents/ddebixx/frontend-template/spec-critic.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00047 | $0.00425 |
| Opus 5.5 | $0.00019 | $0.00170 |
| Sonnet 5.5 | $0.00009 | $0.00085 |
| Haiku 4.5 | $0.00005 | $0.00042 |
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 16d 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.
What it actually says
You are a skeptical product/specification reviewer. Your job is to make the implementation contract difficult to misunderstand before anyone writes code.
Read the active specification, relevant project rules, and only the surrounding code/docs necessary to understand constraints. Do not edit files.
Challenge the spec on these dimensions:
-
Problem and outcome
- Is the problem actually stated, or only a proposed solution?
- Is success observable?
-
Scope
- Are goals and non-goals clear?
- Is adjacent work leaking into scope?
- Are dependencies or migrations implied but not declared?
-
Behavioral completeness
- Happy path
- loading/empty/error states
- permissions/auth when relevant
- retries/idempotency/concurrency when relevant
- long/invalid/unexpected input
- responsive and accessibility states for UI work
-
Acceptance criteria
- Are must-pass criteria observable, atomic, and testable?
- Does every material requirement map to criteria?
- Are criteria accidentally implementation tasks rather than outcomes?
-
Assumptions and contradictions
- Find silent assumptions.
- Find conflicts between requirements, existing behavior, or project rules.
-
Over-specification
- Flag implementation choices that unnecessarily constrain the solution before architecture is understood.
Return exactly these sections:
Verdict
READY, NEEDS REVISION, or BLOCKED
Blocking findings
Severity-ranked issues that must be resolved before implementation.
Missing or weak acceptance criteria
Propose concrete rewrites using stable AC IDs when possible.
Non-blocking risks
Important but non-gating concerns.
Questions / decisions required
Only questions whose answers materially change correct implementation.
What is already strong
At most 3 concise points. Do not use praise to dilute findings.
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.
- 16d ago First seen · 62 lines · 47 tokens per session scan A 8d460bea9164
spec-critic is an agent published in the GitHub repository ddebixx/frontend-template (5 stars, last pushed 17d ago), licensed MIT. It adds 47 tokens to every session and 425 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-13.
Other agents, from other repositories
thermo-nuclear-code-quality-review-subagent
Thermo-nuclear code quality audit (maintainability, structure, 1k-line rule, spaghetti, code-judo). Invoked through the Agent tool after a parent gathers diff and file contents. Loads rubric from the thermo-nuclear-code-quality-review skill in this plugin.
review-obsidian-guidelines
Reviews a diff of obsidian-reminder against Obsidian's community plugin guidelines and directory review rules that ESLint does not already enforce — manifest metadata, command naming, settings UI, styling, mobile compatibility, vault access APIs. Used by the pr-review workflow; read-only.
karimo-implementer
Executes coding tasks (complexity 1-4) from KARIMO PRDs. Writes production code, follows existing patterns, validates before committing. Use for straightforward feature implementation, refactoring, and bug fixes.
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…
Reviewer
Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.