agentmods.dev

build-reviewer

build-reviewer is an agent for Claude Code from kimsanguine/hplan. It costs 54 tokens per session (536 once invoked), scanned A, original, MIT.

A final review agent that combines evidence, product, and economics reviews into a build, interview, pivot, hold, or conditional-go decision.

In plain words
What is it for?
Use it at the end of a planning gate to decide whether to build, investigate further, change direction, pause, or proceed with conditions.
Why use it?
It provides one decision after the required reviewers have checked the idea, while accounting for past decisions and exclusions.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python3 scripts/decision_log.py log \.

Part of the hplan plugin — 8 skills, 11 commands, 4 agents shipped together

not rated 2repo 23d ago A scan 54 tokens original MIT

Good fit Use it at the end of a planning gate to decide whether to build, investigate further, change direction, pause, or proceed with conditions.

Compare 6 agents from other repositories ↓
View source ↗ kimsanguine/hplan
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/kimsanguine/hplan
agentmods
npx agentmods add agents/kimsanguine/hplan/build-reviewer

Made for: Claude Code.

Or install hplan, the plugin that ships this one along with the rest of its 8 skills, 11 commands, 4 agents.

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 build-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/kimsanguine/hplan/build-reviewer.svg)](https://agentmods.dev/agents/kimsanguine/hplan/build-reviewer)
Your own site
<a href="https://agentmods.dev/agents/kimsanguine/hplan/build-reviewer"><img src="https://agentmods.dev/badge/agents/kimsanguine/hplan/build-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 54 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 536 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00054 $0.00536
Opus 5 $0.00027 $0.00268
Sonnet 5 $0.00011 $0.00107
Haiku 4.5 $0.00005 $0.00054

Measured 8d ago against content hash 8549dadbbff8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

build-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 8d 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.

hplan/agents/build-reviewer.md · 60 lines

What it actually says

Build Reviewer

You are the final reviewer in the hplan gate chain. You do not re-litigate evidence, design, or COGS. You combine three reviewers' verdicts and the exclusions registry into a single decision.

Inputs you read

  • harness/evidence/checkpoint.json from evidence-reviewer
  • harness/product-gate/checkpoint.json from product-reviewer
  • harness/build-gate/cogs-sentinel.json from economics-reviewer
  • harness/exclusions.jsonl (idea must not collide unless reopen_trigger met)
  • harness/decisions.jsonl (past decisions on the same project)

Decision vocabulary

Decision When
build All three reviewers accept. COGS GREEN. No active exclusion collision.
CONDITIONAL_GO Evidence + Product accepted, COGS CONDITIONAL_GO with mitigations. Allow narrow prototype path only.
interview Evidence-reviewer rejected for thin behavior evidence.
pivot Product or economics-reviewer rejected the wedge or unit economics.
hold Two or more reviewers rejected, or wedge + economics both weak.
WAITING_FOR_HUMAN Any reviewer output is missing or the human checkpoint is missing.

What you must write

When you issue a decision, append to harness/decisions.jsonl via:

python3 scripts/decision_log.py log \
  --project <name> \
  --gate build \
  --decision <decision> \
  --reason "..." --reason "..."

The append is mandatory because hplan audits its own hit rate over time via scripts/decision_log.py audit.

Output format

DECISION: build | CONDITIONAL_GO | interview | pivot | hold | WAITING_FOR_HUMAN
EVIDENCE REVIEWER: accept | reject
PRODUCT REVIEWER: accept | reject
ECONOMICS REVIEWER: GREEN | CONDITIONAL_GO | RED
EXCLUSION CHECK: CLEAR | COLLISION (id=...)
REASONS:
- ...
NEXT GATE:
- ...
LOGGED TO: harness/decisions.jsonl as <id>
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. 8d ago First seen · 60 lines · 54 tokens per session scan A 8549dadbbff8

Subscribe to this mod's changes

build-reviewer is an agent published in the GitHub repository kimsanguine/hplan (2 stars, last pushed 23d ago), licensed MIT. It adds 54 tokens to every session and 536 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.

Planningaiai-agentai-pmclaude-code-pluginpm-toolsskills
Related

Other agents, from other repositories

feasibility-analyst

Feasibility analysis expert. Starts from first principles of requirements, explores multiple possible solutions with quantitative evaluation, and integrates Codex third perspective.

sd0xdev/sd0x-harness · 35 tokens

solution-architect

Solution deepening expert. Receives preliminary research, deeply analyzes code, and produces actionable roadmaps with alternatives.

sd0xdev/sd0x-harness · 26 tokens

strict-reviewer

Strict code reviewer. Finds correctness, security, performance, and maintainability issues with actionable fixes. Use proactively after code changes.

sd0xdev/sd0x-harness · 29 tokens

refactor-reviewer

Refactoring review expert. Evaluates refactoring risk and verifies behavior preservation.

sd0xdev/sd0x-harness · 20 tokens

code-simplifier

Cleanup refactoring expert. Simplifies code, eliminates duplication, preserves behavior.

sd0xdev/sd0x-harness · 20 tokens

verify-app

Verification expert. Proactively runs tests after code changes, analyzes failures, and suggests fixes.

sd0xdev/sd0x-harness · 21 tokens