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.
git clone --depth 1 https://github.com/megamen32/LastHumanCommitWrote 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/plugins/megamen32/lasthumancommit/gsd)<a href="https://agentmods.dev/plugins/megamen32/lasthumancommit/gsd"><img src="https://agentmods.dev/badge/plugins/megamen32/lasthumancommit/gsd/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/plugins/megamen32/lasthumancommit/gsd"><img src="https://agentmods.dev/badge/plugins/megamen32/lasthumancommit/gsd.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
gsd 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.
What it actually says
{
"name": "gsd",
"version": "1.42.3",
"description": "Portable full-profile Get Shit Done 1.42.3 Agent Plugin.",
"author": {
"name": "TACHES, packaged by megamen32",
"url": "https://github.com/gsd-build/get-shit-done"
},
"skills": "./skills/"
}
What it installs
The manifest is a name and a version. 67 skills, 33 agents travel with it, and installing the plugin installs all of them — 2,709 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill gsd-graphify A 22 tokens
- Skill gsd-quick A 24 tokens
- Skill gsd-complete-milestone A 16 tokens
- Skill gsd-discuss-phase A 15 tokens
- Skill gsd-map-codebase A 21 tokens
- Skill gsd-plan-phase A 16 tokens
- Skill gsd-autonomous A 19 tokens
- Skill gsd-capture A 17 tokens
- Skill gsd-code-review A 22 tokens
- Skill gsd-docs-update A 16 tokens
- Skill gsd-execute-phase A 17 tokens
- Skill gsd-forensics A 21 tokens
- Skill gsd-import A 18 tokens
- Skill gsd-manager A 14 tokens
- Skill gsd-phase A 21 tokens
- Skill gsd-plan-review-convergence A 25 tokens
- Skill gsd-progress A 23 tokens
- Skill gsd-spike A 23 tokens
- Skill gsd-update A 14 tokens
- Skill gsd-workspace A 20 tokens
- Skill gsd-workstreams A 24 tokens
- Skill gsd-add-tests A 18 tokens
- Skill gsd-ultraplan-phase A 29 tokens
- Skill gsd-undo A 23 tokens
- Skill gsd-debug A 13 tokens
- Skill gsd-review-backlog A 14 tokens
- Skill gsd-new-project A 16 tokens
- Skill gsd-review A 18 tokens
- Skill gsd-config A 21 tokens
- Skill gsd-sketch A 27 tokens
- Skill gsd-ingest-docs A 32 tokens
- Skill gsd-milestone-summary A 20 tokens
- Skill gsd-surface A 23 tokens
- Skill gsd-health A 13 tokens
- Skill gsd-mvp-phase A 26 tokens
- Skill gsd-spec-phase A 23 tokens
- Skill gsd-ns-manage A 16 tokens
- Skill gsd-ns-review A 16 tokens
- Skill gsd-pause-work A 16 tokens
- Skill gsd-secure-phase A 16 tokens
- Skill gsd-ship A 18 tokens
- Skill gsd-fast A 17 tokens
- Skill gsd-inbox A 23 tokens
- Skill gsd-new-milestone A 20 tokens
- Skill gsd-ns-project A 12 tokens
- Skill gsd-profile-user A 16 tokens
- Skill gsd-stats A 20 tokens
- Skill gsd-verify-work A 13 tokens
- Skill gsd-audit-fix A 25 tokens
- Skill gsd-ns-workflow A 15 tokens
- Skill gsd-audit-milestone A 17 tokens
- Skill gsd-eval-review A 26 tokens
- Skill gsd-explore A 20 tokens
- Skill gsd-resume-work A 15 tokens
- Skill gsd-settings A 13 tokens
- Skill gsd-ui-review A 17 tokens
- Skill gsd-validate-phase A 19 tokens
- Skill gsd-ai-integration-phase A 23 tokens
- Skill gsd-audit-uat A 18 tokens
- Skill gsd-ns-context A 16 tokens
- Skill gsd-ns-ideate A 17 tokens
- Skill gsd-pr-branch A 23 tokens
- Skill gsd-thread A 12 tokens
- Skill gsd-ui-phase A 18 tokens
- Skill gsd-cleanup A 12 tokens
- Skill gsd-extract-learnings A 20 tokens
- Skill gsd-help A 12 tokens
- Agent gsd-executor A 36 tokens
- Agent gsd-framework-selector A 54 tokens
- Agent gsd-user-profiler A 36 tokens
- Agent gsd-research-synthesizer A 37 tokens
- Agent gsd-ui-auditor A 40 tokens
- Agent gsd-plan-checker A 35 tokens
- Agent gsd-debugger A 29 tokens
- Agent gsd-intel-updater A 22 tokens
- Agent gsd-planner A 33 tokens
- Agent gsd-code-fixer A 43 tokens
- Agent gsd-phase-researcher A 40 tokens
- Agent gsd-eval-planner A 71 tokens
- Agent gsd-integration-checker A 31 tokens
- Agent gsd-project-researcher A 48 tokens
- Agent gsd-debug-session-manager A 61 tokens
- Agent gsd-advisor-researcher A 32 tokens
- Agent gsd-roadmapper A 36 tokens
- Agent gsd-code-reviewer A 40 tokens
- Agent gsd-domain-researcher A 77 tokens
- Agent gsd-security-auditor A 37 tokens
- Agent gsd-doc-synthesizer A 77 tokens
- Agent gsd-pattern-mapper A 44 tokens
- Agent gsd-eval-auditor A 75 tokens
- Agent gsd-nyquist-auditor A 24 tokens
- Agent gsd-ai-researcher A 67 tokens
- Agent gsd-doc-classifier A 62 tokens
- Agent gsd-ui-researcher A 43 tokens
- Agent gsd-doc-writer A 35 tokens
- Agent gsd-ui-checker A 41 tokens
- Agent gsd-assumptions-analyzer A 31 tokens
- Agent gsd-doc-verifier B 25 tokens
- Agent gsd-codebase-mapper C 46 tokens
- Agent gsd-verifier C 36 tokens
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.
- today First seen · 11 lines scan A 41e496541cce
gsd is a plugin published in the GitHub repository megamen32/LastHumanCommit (2 stars, last pushed today), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-09-12.
Other plugins, from other repositories
nextjs
Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.
themes-example
themes-example. An open-source AI agent that brings the power of Gemini directly into your terminal.
claude-plugins-official marketplace
Directory of popular Claude Code extensions including development tools, productivity plugins, and MCP integrations.
humanizer
Rewrite AI-sounding text so it reads naturally without changing what it says.
knowledge-work-plugins marketplace
Plugin marketplace listing 104 plugins: noibu, productivity, enterprise-search, cowork-plugin-management, sales.
container
Teaches Claude container's command surface and how it maps to Docker, Lima, Colima, and Podman on macOS.