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 commands/satoruogojoo/octopus/debuggit clone --depth 1 https://github.com/SatoruoGojoo/octopusWrote 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/commands/satoruogojoo/octopus/debug)<a href="https://agentmods.dev/commands/satoruogojoo/octopus/debug"><img src="https://agentmods.dev/badge/commands/satoruogojoo/octopus/debug.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 | $0.00038 | $0.00327 |
| Opus 5 | $0.00019 | $0.00163 |
| Sonnet 5 | $0.00008 | $0.00065 |
| Haiku 4.5 | $0.00004 | $0.00033 |
Grade A, and why
debug scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
用 Agent 工具啟動 debugger agent，把錯誤資訊原文（含截圖/log）完整轉給它。
- 它若反問（最多 2 問），轉給使用者後把答案轉回（SendMessage 延續同一個 agent）
- 它只分析不修檔；產出根因報告後完整轉述給使用者，保留「確認 vs 推測」的區分，不要擅自把推測講成定論
- 使用者決定修法後，看修法會不會改變預期行為：
- 不會（code 沒做到 spec 本來就寫的事）→ 直接在對話中處理，不進管線
- 會變，或查證後發現該行為從未被寫進主 spec → 走
/octopus:spec開 change（修法本身就是需求），把根因報告全文一併轉入——該 change 的 delta 須把實際炸過的失敗案例編碼成至少一個 Scenario（回歸防護進 spec）
問題：$ARGUMENTS
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.
- 4d ago First seen · 15 lines · 38 tokens per session scan A c9f0bde372ef
debug is a command published in the GitHub repository SatoruoGojoo/octopus (2 stars, last pushed 3d ago), licensed MIT. It adds 38 tokens to every session and 327 once invoked, about $0.0002 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.
Other commands, from other repositories
sync
Sync the audit manifest with Azure DevOps work items — set the connector up for the first time (connect: verify the transport, report which auth path is in effect, prove access read-only, detect the board's process), push manifest bugs/tasks/phases to ADO (board states, sprint stamp, Remaining Work, comments), pull…
init
Multi-agent codebase audit that GENERATES the audit manifest (phases/tasks) at manifestPath. Interviews you for scope/goals, fans out parallel read-only explorers, synthesizes findings, then presents the proposed phases for approval BEFORE writing — approve to materialize, or park them as proposals for later…
task
Add a tracked task to the audit manifest — every answer is a flag, and the dialogue only covers what the caller did not pass — move one between phases, or cancel work that will not be done. add allocates the id, initializes all orchestrator fields, updates fileIndex, and revalidates; move renumbers a task into another…
panel
Audit pipeline: open / stop / check a local control-panel UI to visually manage .claude/audit.config.json and the manifest's composition levers (reviewSkill, per-task skills/models, buildCommands) — with live validation and discovery of the skills & agents available in this repo + globally. Ephemeral, on-demand; a…
doctor
Audit pipeline: diagnose the setup before it bites — interpreter the hooks will use, git root, config, manifest + shard integrity, which plan-gate tier is active, submodule conflicts, build runners, whether the skills the plan names would resolve from a clone or only here, whether hooks have ever fired and which copy…
layout
Audit pipeline: choose how the manifest is stored — sharded (an index plus one file per phase: fewer tokens per phase run, parallel-safe across worktrees) or single-file (one file, one diff, no index). A layout CHOICE, not a version upgrade: both shapes are current, neither goes out of date, and this command moves in…