cocosearch-debugging

cocosearch-debugging is a skill for Claude Code, Codex from VioletCranberry/coco-search. It costs 37 tokens per session (2,713 once invoked), scanned A, original, MIT.

A debugging guide that uses CocoSearch, a code search system that finds related symbols and meaning across an indexed project, to trace errors and code flow.

In plain words
What is it for?
Use it when investigating errors, unexpected behavior, dependency drift, or the path a request takes through a codebase.
Why use it?
It helps locate likely causes by checking the project's search index, freshness, dependencies, and related code instead of searching files manually.

Skill for Claude CodeCodex

Part of the cocosearch plugin — 12 skills 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/violetcranberry/coco-search/cocosearch-debugging
Any agent
npx skills add VioletCranberry/coco-search --skill cocosearch-debugging
Clone the repo
git clone --depth 1 https://github.com/VioletCranberry/coco-search

Made for: Claude Code, Codex.

Or install cocosearch, the plugin that ships this one along with the rest of its 12 skills.

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 cocosearch-debugging

README.md
[![agentmods](https://agentmods.dev/badge/skills/violetcranberry/coco-search/cocosearch-debugging.svg)](https://agentmods.dev/skills/violetcranberry/coco-search/cocosearch-debugging)
Your own site
<a href="https://agentmods.dev/skills/violetcranberry/coco-search/cocosearch-debugging"><img src="https://agentmods.dev/badge/skills/violetcranberry/coco-search/cocosearch-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 2,713 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 $0.00037 $0.02713
Opus 5 $0.00018 $0.01357
Sonnet 5 $0.00007 $0.00543
Haiku 4.5 $0.00004 $0.00271

Measured 5d ago against content hash 13cd441116a2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cocosearch-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.

skills/cocosearch-debugging/SKILL.md · 350 lines

How it starts

The opening of the file, as written. The whole thing — 350 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Debugging with CocoSearch

Pre-flight Check

  1. Resolve index name (use the resolved name for all operations):
    • Try cocosearch.yaml for indexName field -- if found, use it
    • If no config file, call list_indexes() and match the current project's directory name against available indexes. The MCP tools auto-derive index names from directory paths (e.g., my-project/ -> my_project), so a match is likely if the repo was indexed without a config file.
    • If no match found, the project is genuinely not indexed -- offer to index it. Do NOT abandon CocoSearch tools just because cocosearch.yaml is missing.
  2. list_indexes() to confirm project is indexed
  3. index_stats(index_name="<resolved-name>") to check freshness
  • No index → offer to index before debugging
  • Stale (>7 days) → warn: "Index is X days old -- results may not reflect recent changes. Want me to reindex first?"
  1. Check dependency freshness — call get_file_dependencies on any known file from the error context:

    get_file_dependencies(file="<file-from-error>", depth=1)
    
    • If response contains warnings with type deps_outdated or deps_branch_drift: Warn: "Dependency data is outdated — call chain tracing may be incomplete. Want me to re-extract dependencies first?"
    • If response contains warnings with type deps_not_extracted: Note: "No dependency data found. I'll use search-based call tracing instead. Dependency data can improve tracing accuracy — want me to extract dependencies?"
    • If no warnings: Proceed normally (use dependency Fast Path when applicable).
  2. Linked index health (if cocosearch.yaml has linkedIndexes):

    • Check the warnings array from index_stats() for entries starting with "Linked index"
    • If stale/missing: warn user — "Linked index 'X' is stale/missing. Cross-project results may be incomplete. Want me to reindex?"

Step 1: Understand the Symptom

Parse what the user is reporting. Different inputs require different extraction:

Read the full file on GitHub · 350 lines

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 · 350 lines · 37 tokens per session scan A 13cd441116a2

Subscribe to this mod's changes

cocosearch-debugging is a skill published in the GitHub repository VioletCranberry/coco-search (37 stars, last pushed today), licensed MIT. It adds 37 tokens to every session and 2,713 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 2026-08-30.

Related

Other skills, from other repositories

codebase-search

Semantic code and documentation search by meaning. Use codebasepeek to find WHERE code is (saves tokens), codebasesearch to see actual code. For exact identifiers, use grep instead. Search local codebase before using websearch for code/library/API/example questions.

Helweg/open-codebase-index · 58 tokens

gno

Search local documents, files, notes, and knowledge bases. Index directories, search with BM25/vector/hybrid, get AI answers with citations. Use when user wants to search files, find documents, query notes, look up information in local folders, index a directory, set up document search, build a knowledge base, needs…

gmickel/gno · 86 tokens

embeddings-search

Use when choosing an embedding model, chunk size, or query form, when semantic search returns irrelevant results, when adding hybrid BM25+vector or a reranker, or when a retrieval change needs a number (recall@k, nDCG, MRR). NOT operating the store — index tuning, quantization (that is vector-db) — nor the…

ericrisco/rsc-harness · 88 tokens

codebase-search

Preferred local codebase-understanding workflow for Pi and Codex. Start with codebasecontext before shell search or broad reads, then use specialized semantic and graph tools.

Helweg/open-codebase-index · 37 tokens

rag-expert

Design retrieval-augmented generation systems: chunking, embeddings, vector and hybrid search, reranking, grounding and evaluation. Use when the user mentions RAG, retrieval, semantic search, embeddings, vector databases, pgvector, Chroma, Qdrant, Pinecone, chunking or reranking, wants an assistant answering over…

personamanagmentlayer/pcl · 97 tokens

vera

Code search over the current repository. Before reading files to answer "where is X", "how does Y work", "find Z", or "what calls W", run vera search " " or vera references first. Use vera grep for exact strings and regex, vera structural for definitions, routes, and env reads. Do not read multiple files hoping to…

VeraTools/Vera · 96 tokens