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.
git clone --depth 1 https://github.com/s977043/PlanGatenpx agentmods add skills/s977043/plangate/hypothesis-loggerWrote 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/skills/s977043/plangate/hypothesis-logger)<a href="https://agentmods.dev/skills/s977043/plangate/hypothesis-logger"><img src="https://agentmods.dev/badge/skills/s977043/plangate/hypothesis-logger/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/skills/s977043/plangate/hypothesis-logger"><img src="https://agentmods.dev/badge/skills/s977043/plangate/hypothesis-logger.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 | $0.00088 | $0.01176 |
| Opus 5.5 | $0.00035 | $0.00470 |
| Sonnet 5.5 | $0.00018 | $0.00235 |
| Haiku 4.5 | $0.00009 | $0.00118 |
Grade A, and why
hypothesis-logger 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 1mo 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hypothesis Logger
正本:
.claude/skills/hypothesis-logger/SKILL.md関連:docs/workflows/07_exploratory_debug.mdPhase E-1
WF-07 探索的デバッグの仮説→検証→学習→AC 更新サイクルを構造化して記録する。
手順
Step 1: 仮説番号の採番
docs/working/<TASK-XXXX>/status.md のすべての「仮説-N:」プレフィックスのエントリ（完了済み - [x]・未完了 - [ ] 問わず）を走査し、最大の N を特定して N+1 を採番する（存在しない場合は 仮説-1 から始める）。完了済み仮説をカウントから除外すると番号が重複するため、完了状態に関わらず全件を対象にする。
Step 2: status.md への仮説記録
docs/working/<TASK-XXXX>/status.md の残タスクに以下の形式で追記する:
- [ ] 仮説-N: <仮説の説明（1 行）>
prediction: <検証すれば何が分かるか>
verification: <どうやって検証するか（コマンド / ビルド / 手順）>
waiting_external_verification: <true|false>
waiting_external_verification: true の場合は BLOCKED 状態として扱う（working-context.md §BLOCKED 状態 準拠）。
Step 3: evidence ディレクトリへの詳細記録
docs/working/<TASK-XXXX>/evidence/exploratory/hypothesis-N.md を作成する:
# 仮説-N: <タイトル>
## 仮説
<詳細な仮説の説明>
## 検証手順
<再現性のある手順>
## 予測結果
<成功 / 失敗の判断基準>
## 検証結果
<!-- 検証完了後に記入 -->
- 結果: <RESOLVED|REJECTED|DEFERRED>
- 判明した事実: <text>
- 次の仮説: <text or なし>
## AC への影響
<!-- 前提変更があれば記入 -->
- 影響 AC: <ID or なし>
- 変更内容: <text>
Step 4: 検証結果の記録（検証完了後）
検証が完了したら以下を実施する:
evidence/exploratory/hypothesis-N.mdの「検証結果」セクションを記入status.mdの- [ ] 仮説-N:を- [x]に更新し、結果を 1 行追記- AC への影響がある場合（Phase E-3 発動条件）:
pbi-input.mdの Notes に「前提変更 (仮説-N 由来)」として追記test-cases.mdの該当 AC を更新- 影響が Out of scope を超える場合は人間に C-3 再承認を求める
完了状態
| 状態 | 意味 |
|---|---|
RESOLVED |
仮説が正しく、問題が解消された |
REJECTED |
仮説が外れた（問題は別の原因）→ 次の仮説へ |
DEFERRED |
外部依存で検証待ち（BLOCKED 状態に移行） |
使用例
入力: 「EAS ビルドが失敗する原因として .gitignore の glob 誤マッチが怪しい。仮説を記録して」
出力イメージ (status.md への追記):
- [ ] 仮説-3: .gitignore の `pr*.json` glob が `primitive.json` を誤マッチしている
prediction: glob を修正すれば EAS が primitive.json を含める
verification: .gitignore を修正して EAS production build を再実行
waiting_external_verification: true
関連
- WF-07:
docs/workflows/07_exploratory_debug.md - BLOCKED 状態:
.claude/rules/working-context.md§BLOCKED 状態
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.
- 1mo ago First seen · 96 lines · 88 tokens per session scan A 8ad4adf7f1ab
hypothesis-logger is a skill published in the GitHub repository s977043/PlanGate (2 stars, last pushed yesterday), licensed MIT. It adds 88 tokens to every session and 1,176 once invoked, about $0.0004 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 2026-09-03.
Other skills, from other repositories
postmortem
Auto-generates a structured postmortem from a completed campaign. Reads the campaign file, telemetry logs, and feature ledger. Produces a documented analysis of what broke, what the safety systems caught, and what patterns emerged. Can also be invoked manually for any incident.
systematic-debugging
4-phase root cause analysis: observe, hypothesize, verify, fix. Enforces investigation before any code changes. Emergency stop after 2 failed fixes. Prevents shotgun debugging and fix cascades.
04-audit
Audit a codebase read-only across seven quality pillars into one ranked report. Use when the user wants to assess, health-check, or audit a codebase or one pillar. Not for fixing findings, reviewing a change, or checking a feature works.
07-refactor
Improve code across four axes (cleanup, performance, security, architecture) by scanning and fixing, or applying a pushed audit report. Use when the user wants to refactor, optimize, harden, or remove code. Not for read-only diagnosis or adding tests.
03-assert
Assert the work behaves by iterating the project's coding assertions until they pass, plus optional architecture and frontend facets. Use to validate an implementation. Not for reviewing or writing tests.
08-debug
Reproduce and fix a known bug, or find an unknown root cause by hypothesis validation. Use when the user wants to fix a bug, find why something breaks, or reopen a stuck investigation. Not for building a feature or reviewing a diff.