gsd-debug

gsd-debug is a skill for Claude Code from megamen32/LastHumanCommit. It costs 13 tokens per session (1,428 once invoked), scanned A, a copy of gsd-add-tests, MIT.

A systematic debugging workflow that keeps its state while investigating a problem, including across context resets.

In plain words
What is it for?
Use it to track the cause of a bug and continue the investigation after the working context changes.
Why use it?
It reduces the risk of losing investigation notes, evidence, or next steps during a long debugging session.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions subagents; names the AskUserQuestion tool; mentions Claude Code.

Part of the gsd plugin — 67 skills, 33 agents shipped together

Good fit Use it to track the cause of a bug and continue the investigation after the working context changes.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/megamen32/lasthumancommit/gsd-debug
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.

Any agent
npx skills add megamen32/LastHumanCommit --skill gsd-debug
Clone the repo
git clone --depth 1 https://github.com/megamen32/LastHumanCommit

Made for: Claude Code.

Or install gsd, the plugin that ships this one along with the rest of its 67 skills, 33 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 gsd-debug

README.md
[![agentmods](https://agentmods.dev/badge/skills/megamen32/lasthumancommit/gsd-debug/github.svg)](https://agentmods.dev/skills/megamen32/lasthumancommit/gsd-debug)
Your own site
<a href="https://agentmods.dev/skills/megamen32/lasthumancommit/gsd-debug"><img src="https://agentmods.dev/badge/skills/megamen32/lasthumancommit/gsd-debug/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.

agentmods 80×15 button for gsd-debug

Your own site · 80×15
<a href="https://agentmods.dev/skills/megamen32/lasthumancommit/gsd-debug"><img src="https://agentmods.dev/badge/skills/megamen32/lasthumancommit/gsd-debug.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 13 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,428 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 81% copy Near-identical to another mod 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 $0.00013 $0.01428
Opus 5 $0.00006 $0.00714
Sonnet 5 $0.00003 $0.00286
Haiku 4.5 $0.00001 $0.00143

Measured today against content hash aa04c145b85f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

gsd-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 today.

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.

Origin

This is a copy

81% identical to gsd-add-tests — 43 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

plugins/gsd/skills/gsd-debug/SKILL.md · 122 lines

How it starts

The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.

<gsd_agent_plugin_adapter> This GSD distribution is loaded from an Agent Plugin rather than a fixed runtime home.

  • Resolve GSD_PLUGIN_ROOT as the absolute directory two levels above this SKILL.md.
  • Resolve every @../../... execution-context reference relative to this skill directory.
  • Before running a workflow shell command, replace gsd-sdk with node "$GSD_PLUGIN_ROOT/bin/gsd-sdk.js" and turn any ../../get-shit-done/... command path into an absolute path below $GSD_PLUGIN_ROOT.
  • Named GSD agent prompts live in $GSD_PLUGIN_ROOT/agents/. If the runtime has no matching registered agent type, spawn an available generic worker/default agent and include the corresponding agents/<name>.md prompt in its task message. </gsd_agent_plugin_adapter>

<codex_skill_adapter>

A. Skill Invocation

  • This skill is invoked by mentioning $gsd-debug.
  • Treat all user text after $gsd-debug as {{GSD_ARGS}}.
  • If no arguments are present, treat {{GSD_ARGS}} as empty.

B. AskUserQuestion → request_user_input Mapping

GSD workflows use AskUserQuestion (Claude Code syntax). Translate to Codex request_user_input:

Parameter mapping:

  • headerheader
  • questionquestion
  • Options formatted as "Label" — description{label: "Label", description: "description"}
  • Generate id from header: lowercase, replace spaces with underscores

Batched calls:

  • AskUserQuestion([q1, q2]) → single request_user_input with multiple entries in questions[]

Multi-select workaround:

  • Codex has no multiSelect. Use sequential single-selects, or present a numbered freeform list asking the user to enter comma-separated numbers.

Execute mode fallback:

  • When request_user_input is rejected or unavailable, you MUST stop and present the questions as a plain-text numbered list, then wait for the user's reply. Do NOT pick a default and continue (#3018).
  • You may only proceed without a user answer when one of these is true: (a) the invocation included an explicit non-interactive flag (--auto or --all), (b) the user has explicitly approved a specific default for this question, or (c) the workflow's documented contract says defaults are safe (e.g. autonomous lifecycle paths).
  • Do NOT write workflow artifacts (CONTEXT.md, DISCUSSION-LOG.md, PLAN.md, checkpoint files) until the user has answered the plain-text questions or one of (a)-(c) above applies. Surfacing the questions and waiting is the correct response — silently defaulting and writing artifacts is the #3018 failure mode.

Read the full file on GitHub · 122 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. today First seen · 122 lines · 13 tokens per session scan A aa04c145b85f

Subscribe to this mod's changes

gsd-debug is a skill published in the GitHub repository megamen32/LastHumanCommit (2 stars, last pushed today), licensed MIT. It adds 13 tokens to every session and 1,428 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 81% identical to gsd-add-tests, differing in 43 lines, and is treated as a copy.

Related

Other skills, from other repositories

debug-optimize-lcp

Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…

ChromeDevTools/chrome-devtools-mcp · 99 tokens

systematic-debugging

Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.

open-metadata/OpenMetadata · 37 tokens

diagnose

Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.

emdash-cms/emdash · 43 tokens

repro-admin

Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.

emdash-cms/emdash · 48 tokens

log-error-digest

Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…

zebbern/claude-code-guide · 71 tokens

byted-util-volcengine-detect-retry

An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.

bytedance/agentkit-samples · 101 tokens