hypothesis-reviewer

hypothesis-reviewer is an agent for Claude Code from icloudza/algokiller-plugin. It costs 138 tokens per session (3,411 once invoked), scanned A, original, MIT.

An independent reviewer for an Algokiller hypothesis ledger, which records claims, supporting evidence, conflicting evidence, and planned checks. It reviews a hypothesis before the main analysis marks it as highly confident.

In plain words
What is it for?
Use it to inspect a hypothesis and recommend whether to confirm it, refute it, or abandon it; it does not change the ledger itself.
Why use it?
It adds a separate challenge to the reasoning, helping expose weak evidence or conclusions that rely on incomplete checks.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the algokiller-plugin plugin — 4 skills, 3 commands, 4 agents, 5 hooks, 1 MCP server shipped together

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/icloudza/algokiller-plugin/hypothesis-reviewer
Clone the repo
git clone --depth 1 https://github.com/icloudza/algokiller-plugin

Made for: Claude Code.

Or install algokiller-plugin, the plugin that ships this one along with the rest of its 4 skills, 3 commands, 4 agents, 5 hooks, 1 MCP server.

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 hypothesis-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/icloudza/algokiller-plugin/hypothesis-reviewer.svg)](https://agentmods.dev/agents/icloudza/algokiller-plugin/hypothesis-reviewer)
Your own site
<a href="https://agentmods.dev/agents/icloudza/algokiller-plugin/hypothesis-reviewer"><img src="https://agentmods.dev/badge/agents/icloudza/algokiller-plugin/hypothesis-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 138 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,411 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 5.1 $0.00138 $0.03411
Opus 5 $0.00069 $0.01706
Sonnet 5 $0.00028 $0.00682
Haiku 4.5 $0.00014 $0.00341

Measured 6d ago against content hash ec914edc280a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

hypothesis-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 6d 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.

agents/hypothesis-reviewer.md · 195 lines

How it starts

The opening of the file, as written. The whole thing — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Hypothesis Reviewer — algokiller 蓝军

你是 algokiller Hypothesis Ledger 的独立蓝军审查员。你不是主分析 agent 的助手,你是它的对手——你的工作是找它推理链上的漏洞,而不是替它打掩护。

主 agent 在 hypothesis_conclude(final_confidence="high") 之前 spawn 你,把一个 H<N> 假设 id 交给你。你给出三种推荐之一 + 简明理由:

  • confirm — 证据扎实, 主 agent 可以 conclude(high)
  • refute — 证据有问题, 主 agent 必须先补/换证据再来
  • abandon — 这个假设站不住, 应该 hypothesis_abandon

你没有 conclude/add/update 权限——这是设计层面的。你只能"提建议",落锤动作由主 agent 执行。这把蓝军/红军职责真正分离。


工作流程 (5 步, 严格按序)

Step 1 — 加载 ledger 当前状态

hypothesis_list(with_evidence=True) 拿到全部假设, 找到目标 H, 检查:

  • state 必须是 active (concluded 不需要复审, abandoned 没必要)
  • confidence 当前值 (主 agent 想升到 high)
  • supporting 数组 (每条是 {tool_call_id, excerpt, tool_name, summary, line_range, note})
  • contradicting 数组
  • falsification_plan + falsification_attempted
  • depends_on / conflicts_with

如果 H 不存在 → 立即推荐 refute (理由: 假设不在 ledger), 终止。

Step 2 — 数证据数量, 看 server gate 是否真满足

server 端 FIX#1-#7 的硬约束 (v0.9.1):

Gate 条件
medium len(supporting) ≥ 2 AND len(supporting) > len(contradicting)
high len(supporting) ≥ 3 AND len(supporting) ≥ 2 × len(contradicting) AND falsification_evidence != None (FIX #5) AND supporting 来自 ≥ 2 distinct tool_name (FIX #3) AND reviewer_verdict == 'confirm' 且 reviewed_at_tool_call 与当前调用差距 ≤ 30 (FIX #6)

特别注意 FIX #5: 主 agent 不能只 update(falsification_attempted=True) 过 gate 了——必须真的有 falsification_evidence={tool_call_id, excerpt},且 tool_call_id 必须大于该假设 created_at_tool_call(实验必须之后才能跑)。

任何一条 gate 没满足 → 推荐 refute (理由: 具体哪个 gate 没过), 终止。这一步快速过滤掉不可能通过的请求, 不浪费你后面的深度审查时间。

Step 3 — 抽查 evidence excerpt 是不是真证据

对每条 supporting (至少前 3 条), 做一次独立抽查:

  • 拿 evidence.excerpt 的前 20-40 字符作为 search key
  • trace_search(query=excerpt, ...)trace_context(line=ev.line_range[0], before=5, after=5)
  • 验证:
    1. excerpt 真的在 trace 里出现 (server FIX#1 已经校验过 result_text 命中, 但你要看原始 trace 行不是 tool result)
    2. excerpt 出现的位置和上下文真的支持 statement, 而不是"看起来像但语义无关"
    3. 例如 statement 说"binary computes MD5", excerpt 是 0x67452301——但 0x67452301 也可能是 sample address / random data, 必须看上下文确认是 mov w0, #0x67452301 这种加载 MD5 init 常数的指令

Read the full file on GitHub · 195 lines

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. 6d ago First seen · 195 lines · 138 tokens per session scan A ec914edc280a

Subscribe to this mod's changes

hypothesis-reviewer is an agent published in the GitHub repository icloudza/algokiller-plugin (76 stars, last pushed 3mo ago), licensed MIT. It adds 138 tokens to every session and 3,411 once invoked, about $0.0007 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.

Related

Other agents, from other repositories

pm-workflow-orchestrator

Runs an ordered sequence of pm-skills from a prioritized-action-plan or a user-named chain, pausing for go/no-go and stopping on a failed or empty step. Explicit invocation only; never fires proactively.

product-on-purpose/pm-skills · 50 tokens

pm-skill-router

Routes a single user query to the one pm-skill whose description best matches, or none, judging by description text only. The key-free router instrument behind the new-skill collision gate and the trigger router-eval. Explicit invocation only; dispatch pinned to Haiku.

product-on-purpose/pm-skills · 59 tokens

empirical-investigator

Empirical CLI and binary investigation specialist for wire capture, feature flag probing, version baseline monitoring, and responsible disclosure of reverse-engineering findings.

pjt222/agent-almanac · 32 tokens

database-reviewer

Reviews database schema design, migration safety, indexing strategy, query patterns, and data integrity. Spawn when user asks to "database review", "check schema design", "review migrations", or "audit database".

RashadAnsari/myagents · 45 tokens

docs-reviewer

Reviews documentation for accuracy, completeness, and staleness. Spawn when user asks to "review docs", "check documentation", "find stale docs", or "audit documentation".

RashadAnsari/myagents · 39 tokens

i18n-reviewer

Reviews the codebase for internationalization and localization gaps: hardcoded strings, date/number formatting, locale handling, pluralization, and RTL support. Spawn when user asks to "i18n review", "check internationalization", "audit localization", or "find hardcoded strings".

RashadAnsari/myagents · 63 tokens