Agent skill · data analytics · jeremylongshore
repo-scanning
Internal process for the repo-scanner agent. Defines the step-by-step procedure for scanning GitHub repos for evidence that supports or explains bug clusters. Not user-invocable — loaded by the repo-scanner agent through its skills frontmatter.
Why this skill is useful
Adds a detailed procedure for scanning GitHub repos that includes specific API calls and evidence tier assignments not commonly known.
What it needs
Requires github account access. About 3k tokens when loaded. Last updated 2026-08-07. 2,604 stars on the source repository.
What this skill does
Repo Scanning Process Step-by-step procedure for scanning GitHub repos to gather corroborating evidence for bug clusters, assigning confidence tiers to each finding. Overview Loaded by the repo-scanner agent inside the x-bug-triage plugin. Walks each clustered bug through a fixed evidence-gathering pipeline against the up-to-three repos most likely to host the bug: matching open/recent issues, recent commits in the impact window, affected code paths, and recent deploys correlated to the cluster's firstseen timestamp. Each finding is graded against the evidence-tier policy and recorded as cluster evidence. Prerequisites Cluster table populated upstream by the bug-clustering stage surfacerepomapping configured for every productsurface present in clusters Triage MCP server reachable for mcptriagesearchissues, mcptriageinspectrecentcommits, mcptriageinspectcodepaths, and mcptriagecheckrecentdeploys GitHub access tokens with read scope on the target repos Instructions Step 1: Select Repos For each cluster: 1. Look up repos from surfacerepomapping using the cluster's productsurface 2. Cap at top 3 repos per cluster (hard limit — never scan more) 3. If no mapping exists, note it as a warning and skip Step 2: Search Issues For each repo, call mcptriagesearchissues with the cluster's symptoms and errorstrings: Match error strings against open/recent issues Assign evidence tier based on match confidence Step 3: Inspect Recent Commits Call mcptriageinspectrecentcommits for each repo: 7-day window from current date Filter by affected paths if known from the cluster's featurearea Look for commits that touch relevant code paths Step 4: Inspect Code Paths Call mcptriageinspectcodepaths with the cluster's surface and featurearea: Identify likely affected code paths Check for recent changes or known fragile areas Step 5: Check Recent Deploys Call mcptriagecheckrecentdeploys for each repo: Correlate deploy/release timing with cluster's firstseen timestamp Recent deploy near firstseen …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills jeremylongshore/repo-scanning