cross-repo-debugging

cross-repo-debugging is a skill for Claude Code, Codex from MarcinHamiga/code-indexing-mcp. It costs 37 tokens per session (749 once invoked), scanned A, original, MIT.

A debugging workflow for failures that cross two or more code repositories. A repository is a separate project or codebase; the process traces the failure across producers, data contracts, transport, and consumers.

In plain words
What is it for?
It is for tracing cross-project bugs through APIs, serialized data, generated clients, validation, and contract versions.
Why use it?
It helps distinguish the first broken boundary from later copied errors or misleading search matches. This is useful when separate projects exchange data or generated clients.

Skill for Claude CodeCodex

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/marcinhamiga/code-indexing-mcp/cross-repo-debugging
Any agent
npx skills add MarcinHamiga/code-indexing-mcp --skill cross-repo-debugging
Clone the repo
git clone --depth 1 https://github.com/MarcinHamiga/code-indexing-mcp

Made for: Claude Code, Codex.

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 cross-repo-debugging

README.md
[![agentmods](https://agentmods.dev/badge/skills/marcinhamiga/code-indexing-mcp/cross-repo-debugging.svg)](https://agentmods.dev/skills/marcinhamiga/code-indexing-mcp/cross-repo-debugging)
Your own site
<a href="https://agentmods.dev/skills/marcinhamiga/code-indexing-mcp/cross-repo-debugging"><img src="https://agentmods.dev/badge/skills/marcinhamiga/code-indexing-mcp/cross-repo-debugging.svg" alt="Measured on agentmods" height="20"></a>
Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 749 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 5.1 $0.00037 $0.00749
Opus 5 $0.00018 $0.00375
Sonnet 5 $0.00007 $0.00150
Haiku 4.5 $0.00004 $0.00075

Measured 5d ago against content hash 3731f0ef933b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

cross-repo-debugging 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 5d 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.

src/code_indexing_mcp/skills/cross-repo-debugging/SKILL.md · 48 lines

How it starts

The opening of the file, as written. The whole thing — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cross-Repo Debugging

Overview

Trace failures as evidence chains across explicit repository boundaries. Rankings, copied errors, and matching symbols are not root-cause proof.

Workflow

  1. Call mcp__code-indexing-mcp__list_projects. Select only related projects by ID or unambiguous path; never substitute search_code(all_projects=true) for deliberate scope.
  2. Write the expected chain, such as producer -> contract -> consumer -> persistence. Treat each boundary as a first-divergence hypothesis.
  3. Check mcp__code-indexing-mcp__project_status when freshness is uncertain. In manual mode, refresh stale indexes with mcp__code-indexing-mcp__index_project before trusting missing results.
  4. Call mcp__code-indexing-mcp__search_across_projects with explicit selectors. Query separately for stable identifiers, producer serialization, consumer validation, and contract versions, aliases, artifacts, or configuration.
  5. If one repository dominates the global ranking, do not infer absence elsewhere. Filter by paths, languages, or kinds, or search overlapping boundary pairs or smaller shards.
  6. Pivot concepts into exact identifiers. Use project-scoped mcp__code-indexing-mcp__find_symbol for declarations and semantic search for usages; find_symbol does not resolve call sites.
  7. Call mcp__code-indexing-mcp__file_outline before mcp__code-indexing-mcp__get_chunk. Fetch only the producer, boundary contract/configuration, and consumer code needed to compare names, casing, fields, versions, routes/topics, status handling, defaults, and environment keys.
  8. Record evidence as project/path:line. Stop when it proves the first broken boundary and why it breaks, or when static analysis narrows the failure to one boundary and names the missing runtime evidence.

Use dynamic request and correlation IDs in logs or traces, not as primary source queries. When static code aligns, request the minimum payload, route/topic, deployment version, configuration, and outcome evidence for the narrowed boundary.

Read the full file on GitHub · 48 lines

Files

What ships with it

1 file 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. 5d ago First seen · 48 lines · 37 tokens per session scan A 3731f0ef933b

Subscribe to this mod's changes

cross-repo-debugging is a skill published in the GitHub repository MarcinHamiga/code-indexing-mcp (0 stars, last pushed today), licensed MIT. It adds 37 tokens to every session and 749 once invoked, about $0.0002 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

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens