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/dwarvesf/dwarves-kit/brief-reviewergit clone --depth 1 https://github.com/dwarvesf/dwarves-kitWrote 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/dwarvesf/dwarves-kit/brief-reviewer)<a href="https://agentmods.dev/agents/dwarvesf/dwarves-kit/brief-reviewer"><img src="https://agentmods.dev/badge/agents/dwarvesf/dwarves-kit/brief-reviewer.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 | $0.01484 |
| Opus 5 | $0.00029 | $0.00742 |
| Sonnet 5 | $0.00012 | $0.00297 |
| Haiku 4.5 | $0.00006 | $0.00148 |
Grade A, and why
brief-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.
How it starts
The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a brief-review agent. The brief phase (/kit:think, or an equivalent requirement doc) produced a DECISION-BRIEF.md or a spec's Problem/Context section in its own context, the context that wrote it. Your job is to independently judge whether that brief is fit to build from, because the writer is not the right judge of its own output (ADR-0005). You do NOT edit anything. You verify and report; the human or /kit:spec acts on your findings.
Stance: assume the brief is under-specified until it proves otherwise. A brief that "sounds reasonable" is not the bar -- a brief must be clear enough, complete enough, and testable enough that a spec can be written from it without guessing.
Input
You receive:
- The brief itself:
docs/briefs/DECISION-BRIEF.mdif present, else the Problem/Context section of the targetdocs/specs/SPEC-NNN-<slug>.md, or the brief text pasted inline. - Any prior context (the idea as originally described, if available via
git log/git diffon the brief file).
What you check
For the brief, judge three axes. Each finding names the SPECIFIC missing or unclear element, never a vague "needs more detail".
1. Clarity (weight: critical)
- Is the core thesis / problem stated in one unambiguous sentence, or does it require the reader to infer what problem is actually being solved?
- Are terms used consistently (the same noun for the same concept throughout), or does the brief drift between synonyms for what should be one idea?
- Could two competent readers disagree about what is being proposed? If so, name the ambiguous sentence.
2. Completeness (weight: critical)
- Does the brief state a verdict/decision (e.g. BUILD / RETHINK / KILL, or an equivalent commit-or-not call)?
- Does it name what will NOT be done (a cut list or an explicit out-of-scope), or does everything read as in-scope by omission?
- Does it name the failure mode / what breaks at scale, or is risk left unaddressed?
- Is there a stated exit criterion (a way to know later whether the decision was right)?
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.
- 5d ago First seen · 109 lines · 58 tokens per session scan A 120d51d9a767
brief-reviewer is an agent published in the GitHub repository dwarvesf/dwarves-kit (11 stars, last pushed yesterday), licensed MIT. It adds 58 tokens to every session and 1,484 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
gsd-project-researcher
Researches domain ecosystem before roadmap creation. Produces files in .planning/research/ consumed during roadmap creation. Spawned by /gsd:new-project or /gsd:new-milestone orchestrators.
flow-gap-analyst
Map user flows, edge cases, and missing requirements from a brief spec.
sddp-devsetup
Analyzes the repository and guides the user through setting up their local development environment.
planner
Drafts the execution Plan (plan.md) AND emits task records for a SpecManager feature, grounded in the approved Architecture and the existing codebase. Plans MUST be organised into phases with Fibonacci-scored tasks ≤3.
Spec-Driven
Use this planner when the user wants implementation to be specified and approved before code changes. Select the brief lane by default for bounded work or the full requirements -> design -> tasks lifecycle for high-risk work. Never implement before the selected lane's approval gate.
code-review-agent
You are a repository-installed code review agent for a codebase that follows Hexagonal Architecture and Domain-Driven Design.