git-top-project-selection

git-top-project-selection is a skill for Claude Code, Codex from haocn-ops/git-top. It costs 63 tokens per session (809 once invoked), scanned A, original, MIT.

A workflow for evaluating open-source projects using Git.Top, including their maintenance, alternatives, evidence, and limitations.

In plain words
What is it for?
Finding projects, inspecting repositories, comparing named options, recommending alternatives, and supporting architecture decisions with provenance.
Why use it?
It helps make dependency or technology choices using project information and stated caveats instead of guesswork.

Skill for Claude CodeCodex

Part of the git-top plugin — 1 skill, 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 skills/haocn-ops/git-top/git-top-project-selection
Any agent
npx skills add haocn-ops/git-top --skill git-top-project-selection
Clone the repo
git clone --depth 1 https://github.com/haocn-ops/git-top

Made for: Claude Code, Codex.

Or install git-top, the plugin that ships this one along with the rest of its 1 skill, 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 git-top-project-selection

README.md
[![agentmods](https://agentmods.dev/badge/skills/haocn-ops/git-top/git-top-project-selection.svg)](https://agentmods.dev/skills/haocn-ops/git-top/git-top-project-selection)
Your own site
<a href="https://agentmods.dev/skills/haocn-ops/git-top/git-top-project-selection"><img src="https://agentmods.dev/badge/skills/haocn-ops/git-top/git-top-project-selection.svg" alt="Measured on agentmods" height="20"></a>
Per session 63 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 809 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 $0.00063 $0.00809
Opus 5 $0.00032 $0.00404
Sonnet 5 $0.00013 $0.00162
Haiku 4.5 $0.00006 $0.00081

Measured 2d ago against content hash 49c26f72161f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

git-top-project-selection 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 2d 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.

plugins/git-top/skills/git-top-project-selection/SKILL.md · 67 lines

How it starts

The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Git.Top Project Selection

Use Git.Top as a public, no-auth project-intelligence source. Prefer the production REST API when MCP is unavailable; use the five-tool core MCP profile when it is connected.

Decision Workflow

  1. Classify the request as discovery, known-project inspection, recommendation, alternatives, comparison, or guided workflow.
  2. Check https://git.top/api/trust before making a high-confidence production recommendation.
  3. Choose the shortest path:
    • Discovery: GET /api/search
    • Known project: GET /api/project/{owner}/{repo}
    • Constrained recommendation: POST /api/recommend
    • Known replacement target: GET /api/alternatives/{project}
    • Named shortlist: POST /api/compare
    • Ambiguous or multi-step decision: POST /api/workflow
  4. Add require_d1=true whenever seed fallback must fail closed.
  5. Inspect the leading candidates before answering. Preserve metadata.source, evidence, confidence, caveats, and verification timestamps.
  6. Compare at least two credible candidates when the user is making an adoption decision, unless only one candidate matches all hard constraints.

Read references/api-contract.md when constructing REST requests, interpreting errors, or formatting a final answer.

MCP Path

When Git.Top MCP is connected, prefer https://git.top/mcp/core and use only shared tool behavior:

  1. Call get_agent_workflow for ambiguous or multi-step selection.
  2. Call search_projects or recommend_project for candidate generation.
  3. Call get_project before making factual claims about a candidate.
  4. Call compare_projects before a final choice between named candidates.
  5. Parse result.content[0].text as JSON before reading fields.

Use the full endpoint https://git.top/mcp only for alternatives, graph, score, quality, benchmark, governance, or GRP tools outside the core profile.

Trust Rules

  • Treat metadata.source=d1 as the required source for high-confidence production claims.
  • Treat metadata.source=seed as fallback evidence and disclose that limitation.
  • Respect /api/trust decisions: answer directly on allow, disclose limitations on caution, and fail closed for high-confidence recommendations on block.
  • Do not collapse quality score, Git.Top score, and data trust score into one claim.
  • Treat collection repositories as resource hubs, not executable project replacements.
  • Preserve metadata.snapshot_id across a multi-call decision. Restart dependent calls when the snapshot changes materially.

Read the full file on GitHub · 67 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 2d ago First seen · 67 lines · 63 tokens per session scan A 49c26f72161f

Subscribe to this mod's changes

git-top-project-selection is a skill published in the GitHub repository haocn-ops/git-top (0 stars, last pushed 3d ago), licensed MIT. It adds 63 tokens to every session and 809 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

potpie-source-ingestion

Use when the user explicitly asks to ingest, refresh, or deeply understand a repository, PR, issue, ticket, runbook, incident report, document, or web link into Potpie. The harness performs todo-driven discovery, uses local/GitHub/integration tools and read-only subagents when available, builds evidence-backed…

potpie-ai/potpie · 82 tokens

potpie-repo-baseline

Use when establishing, refreshing, or deeply understanding a repository's baseline memory in Potpie: purpose, application type, features, services/modules, environments, deploy shape, dependencies, API contracts, datastores, integrations, ownership, and explicit preferences. The harness reads authored and…

potpie-ai/potpie · 75 tokens

graph-mutation-plan

Cookbook for composing an applygraphmutations plan — stable entitykey patterns, the canonical label/edge vocabulary, evidence/invalidation/confidence discipline, and a worked example. Load this when building a non-trivial mutation plan.

potpie-ai/potpie · 51 tokens

obsidian-layout-adjustment

Workflow for working with the user on changing how Obsidian looks using CSS snippets. Use this whenever the user asks to restyle Obsidian, tune a vault's visual layout, adjust tabs, sidebars, note surfaces, properties, backlinks, graph panes, file explorer rows, icons, links, shadows, active states, or CSS snippets.…

Ar9av/obsidian-wiki · 115 tokens

alfworld-locate-target-object

Navigates to a suspected location and identifies a target object. Use when your goal requires finding a specific object (e.g., "potato", "plate") and its location is not immediately known. Moves to a relevant receptacle (like a fridge or cabinet), checks its contents, and outputs the object's location or confirms its…

zjunlp/SkillNet · 74 tokens

scienceworld-growth-focuser

Use when you have planted a seed or need to track a plant's growth stage (sprouting, flowering, reproduction). Applies the 'focus on' action to a specific plant or biological entity to signal intent and monitor its development. Trigger after planting or when you need to observe life cycle progression in the…

zjunlp/SkillNet · 71 tokens