cocosearch-explore

cocosearch-explore is a skill for Claude Code from VioletCranberry/coco-search. It costs 52 tokens per session (2,673 once invoked), scanned A, original, MIT.

A codebase exploration guide for answering how a software project works, tracing flows, and researching specific topics. It offers an autonomous mode for structured findings and an interactive mode with explanations and checkpoints.

In plain words
What is it for?
Use it to investigate a specific feature, subsystem, or flow; provide research to another agent; or explain codebase behavior to a user.
Why use it?
It reduces the time spent searching through unfamiliar code and gives findings in a form suited either to another agent or to a developer asking questions.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions subagents.

Part of the cocosearch plugin — 12 skills shipped together

Good fit Use it to investigate a specific feature, subsystem, or flow; provide research to another agent; or explain codebase behavior to a user.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/violetcranberry/coco-search/cocosearch-explore
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.

Any agent
npx skills add VioletCranberry/coco-search --skill cocosearch-explore
Clone the repo
git clone --depth 1 https://github.com/VioletCranberry/coco-search

Made for: Claude Code.

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-explore

README.md
[![agentmods](https://agentmods.dev/badge/skills/violetcranberry/coco-search/cocosearch-explore.svg)](https://agentmods.dev/skills/violetcranberry/coco-search/cocosearch-explore)
Your own site
<a href="https://agentmods.dev/skills/violetcranberry/coco-search/cocosearch-explore"><img src="https://agentmods.dev/badge/skills/violetcranberry/coco-search/cocosearch-explore.svg" alt="Measured on agentmods" height="20"></a>
Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,673 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00052 $0.02673
Opus 5 $0.00026 $0.01337
Sonnet 5 $0.00010 $0.00535
Haiku 4.5 $0.00005 $0.00267

Measured 8d ago against content hash d78fa5c19cec, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

cocosearch-explore 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 8d 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-explore/SKILL.md · 318 lines

How it starts

The opening of the file, as written. The whole thing — 318 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Codebase Exploration with CocoSearch

A unified exploration skill with two modes:

  • Autonomous mode — non-interactive, structured output. For subagent invocation (Task tool), plan mode research, or when you need findings another agent can consume.
  • Interactive mode — checkpoints at each step, narrative explanations. For direct user questions like "how does X work?"

When to Use This vs Other Skills

Skill Goal Best for
cocosearch-explore Answer a question about the codebase "How does X work?", "Go figure out X", subagent research
cocosearch-onboarding Broad codebase understanding First time in a codebase
cocosearch-debugging Find root cause of a bug Error-driven investigation

Mode Selection

Use autonomous mode when:

  • A subagent needs to research something (via Task tool)
  • Plan mode needs codebase context before proposing changes
  • You need structured findings another agent can consume
  • The question is specific enough for 3-7 searches to answer

Use interactive mode when:

  • The user directly asks "how does X work?"
  • The user wants to understand a flow, subsystem, or concept
  • You want to offer "go deeper" follow-ups

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 -- Autonomous: return FAILED status immediately. Interactive: 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
  • Stale (>7 days) → note in output, proceed with warning
  1. 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?"

Read the full file on GitHub · 318 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. 8d ago First seen · 318 lines · 52 tokens per session scan A d78fa5c19cec

Subscribe to this mod's changes

cocosearch-explore is a skill published in the GitHub repository VioletCranberry/coco-search (37 stars, last pushed 3d ago), licensed MIT. It adds 52 tokens to every session and 2,673 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 2026-08-30.