Install payload
Install payload is broadly covered in current results.
92% (11/12)
Source-backed filter active — add entries to compare trust side by side.
Trust signals across 40 of 50 results
2 trust signals differ in this sample: Source provenance, Submitter
Signals differ on Source provenance, Submitter — add entries to compare before you install.
Rollout signal scan
Biggest gaps: metadata review, package integrity. 0 entries have 2+ required gaps.
Install payload
Install payload is broadly covered in current results.
92% (11/12)
Most at-risk entries in this view
Gitleaks
Missing required: Install payload
GitHub Actions Security Review Capability Pack Skill
No required rollout gaps
GitHub Artifact Attestation Provenance Capability Pack Skill
No required rollout gaps
GitMCP Docs Server
No required rollout gaps
git-machete Branch Hygiene Statusline
No required rollout gaps
Adoption queue
8/50 visible results are in hold tier and need mitigation before adoption.
1 blockers: Metadata review
50/100
Request metadata review from maintainers or internal owners.
Collect package checksum or signed artifact information.
commands/ci-failure-triage · trust review · confidence 67%
1 blockers: Metadata review
50/100
Request metadata review from maintainers or internal owners.
Collect package checksum or signed artifact information.
commands/documentation-refresh · trust review · confidence 67%
1 blockers: Metadata review
50/100
Request metadata review from maintainers or internal owners.
Collect package checksum or signed artifact information.
commands/incident-timeline · trust review · confidence 67%
1 blockers: Metadata review
50/100
Request metadata review from maintainers or internal owners.
Collect package checksum or signed artifact information.
commands/targeted-test-generation · trust review · confidence 67%
1 blockers: Metadata review
50/100
Request metadata review from maintainers or internal owners.
Collect package checksum or signed artifact information.
skills/addy-osmani-agent-skills · trust review · confidence 67%
1 blockers: Metadata review
50/100
Request metadata review from maintainers or internal owners.
Collect package checksum or signed artifact information.
hooks/api-schema-drift-detector · trust review · confidence 67%
1 blockers: Metadata review
50/100
Request metadata review from maintainers or internal owners.
Collect package checksum or signed artifact information.
mcp/argocd-mcp-server · trust review · confidence 67%
1 blockers: Metadata review
50/100
Request metadata review from maintainers or internal owners.
Collect package checksum or signed artifact information.
mcp/backlog-mcp-server · trust review · confidence 67%
Decision confidence
8/50 results are low-confidence and need review before adoption.
Address Metadata review, Package integrity before broader rollout.
54/100
commands/ci-failure-triage · trust review
Address Metadata review, Package integrity before broader rollout.
54/100
commands/documentation-refresh · trust review
Address Metadata review, Package integrity before broader rollout.
54/100
commands/incident-timeline · trust review
Address Metadata review, Package integrity before broader rollout.
54/100
commands/targeted-test-generation · trust review
Address Metadata review, Package integrity before broader rollout.
54/100
skills/addy-osmani-agent-skills · trust review
Address Metadata review, Package integrity before broader rollout.
54/100
hooks/api-schema-drift-detector · trust review
Address Metadata review, Package integrity before broader rollout.
54/100
mcp/argocd-mcp-server · trust review
Address Metadata review, Package integrity before broader rollout.
54/100
mcp/backlog-mcp-server · trust review
Freshness distribution
Median age 53 days; all 12 scanned entries are within 90 days.
Theme distribution
88 distinct themes with no dominant one. Most common: github, claude-code, capability-pack.
88 distinct themes across 24 scanned
Expert GitHub Actions security review capability pack applying documented workflow hardening, GITHUB_TOKEN least privilege, secrets handling, and fork PR safety checks from official GitHub Actions security documentation.
Expert skill for reviewing GitHub Artifact Attestations, release artifact digests, workflow provenance, OIDC boundaries, and public release evidence before an AI agent recommends or publishes build outputs.
Remote MCP server that turns any GitHub repository or GitHub Pages site into a documentation and code context source for AI coding assistants.
Claude Code statusline that uses git-machete branch layout data to show whether the current branch is managed, how many branches are outside the layout, and when fork-point overrides need review.
Claude Code statusline that surfaces sensitive environment-file risk and can optionally run git-secrets as a local pre-commit-style scanner.
Claude Code statusline that reads GitHub REST check runs for the active pull request head commit and summarizes failed, pending, and passing checks.
Claude Code statusline that uses GitHub pull request search qualifiers to show review-requested queue counts for maintainers.
Open-source secret scanner for finding passwords, API keys, tokens, and other credentials in git history, files, directories, and stdin.
Access the entire Harness.io DevOps platform from Claude — CI/CD pipelines, GitOps, feature flags, cloud cost, security testing, chaos engineering, and more — through 11 consolidated tools covering 216 resource types across 36 toolsets, with 32 built-in prompt templates.
Manage Docker and Kubernetes infrastructure from Claude — list environments, inspect containers, manage GitOps workflows, troubleshoot resources, and proxy Docker/K8s API calls — with the official Portainer MCP server generated from the Portainer OpenAPI spec.
Community slash command runbook to refresh stale project documentation after code changes: use git history to find affected docs, compare README commands to package scripts, and flag broken internal links before opening a docs PR.
Expert release changelog generation capability pack for drafting, validating, and publishing user-facing release notes from conventional commits, tags, and GitHub Releases with source-backed review matrices and privacy-safe output.
Expert Claude Code GitLab CI agent capability pack for designing, reviewing, and rolling out GitLab CI agent with source-backed checklists, production rules, and privacy-safe output contracts.
Expert Claude Code analytics adoption capability pack for enabling team and enterprise dashboards, GitHub contribution metrics, adoption tracking, ROI reporting, and OpenTelemetry complements with source-backed rollout steps.
Code research MCP server that gives Claude GitHub code search, repository exploration, PR search, local ripgrep, local file reading, LSP definitions, references, call hierarchy, and package-to-source discovery.
MCP server that unifies web search, AI answer, GitHub search, and web extraction providers including Tavily, Brave, Kagi, Exa, Linkup, Firecrawl, and GitHub behind four consolidated tools.
Built-in HTTP MCP server for Radar, the local-first Kubernetes UI that gives Claude token-optimized cluster topology, health, events, logs, audit, RBAC, GitOps, workload, and resource-management tools.
Open-source framework for building internal coding agents that accept tasks via Slack, Linear, or GitHub, execute code changes in isolated cloud sandboxes, and open draft pull requests automatically.
Slash command that triages a failing GitHub Actions run: it pulls the failed job logs with the GitHub CLI, isolates the first real error, classifies the failure (test, lint, type, build, dependency, or flaky), and proposes a targeted, minimal fix with the exact command to reproduce it locally.
PreToolUse hook that scans the exact text Claude Code is about to write or edit for high-confidence secret formats (AWS access keys, GitHub tokens, OpenAI keys, Slack tokens, Google API keys, Stripe keys, and private key blocks) and blocks the write with a non-zero exit before the secret ever reaches disk.
Claude Code statusline that uses simple-git status data to show dirty worktree risk, staged changes, untracked files, and merge conflicts.
LoopOver MCP connects Claude and other MCP clients to private, metadata-only Gittensor contribution workflows for branch preflight, scoreability estimates, maintainer-fit checks, and public-safe PR packets.
Index any documentation — websites, GitHub repos, npm/PyPI packages, local files — and give Claude always-current, version-specific answers with the open-source Grounded Docs MCP server. An offline-first alternative to Context7, Nia, and Ref.Tools.
Microsoft-maintained Agent Skills, plugins, custom agents, AGENTS.md templates, and MCP configurations for Azure SDKs, Microsoft Foundry, Microsoft 365 Agents SDK, Copilot SDK, MCP server building, and cloud solution work.
Connect Claude to DigitalOcean — manage Apps, Droplets, managed Databases, Kubernetes, Container Registry, networking, and Functions — with DigitalOcean's official Model Context Protocol server.
Community slash command runbook for adding minimal automated tests around a changed module: inspect the git diff, mirror repository test conventions, and draft focused unit or integration tests using Anthropic develop-tests guidance.
Apache-2.0 reactive Python notebook stored as pure Python for reproducible experiments, SQL-backed data workflows, script execution, app deployment, and AI-assisted editing.
Open-source data and model versioning tool for tracking datasets, ML artifacts, pipelines, experiments, metrics, and remote storage alongside Git.
Soothing Catppuccin Mocha theme statusline with 26 pastel colors, Powerline separators, and modular segments for Git, model info, and token tracking.
Open-source terminal coding assistant that edits files in Git repositories using chat-driven development loops.