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.
npx skills add VioletCranberry/coco-search --skill cocosearch-exploregit clone --depth 1 https://github.com/VioletCranberry/coco-searchWrote 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.
[](https://agentmods.dev/skills/violetcranberry/coco-search/cocosearch-explore)<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>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once 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 |
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.
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
- Resolve index name (use the resolved name for all operations):
- Try
cocosearch.yamlforindexNamefield -- 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.yamlis missing.
- Try
list_indexes()to confirm project is indexedindex_stats(index_name="<resolved-name>")to check freshness
- Stale (>7 days) → note in output, proceed with warning
- Linked index health (if
cocosearch.yamlhaslinkedIndexes):- Check the
warningsarray fromindex_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?"
- Check the
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.
- 8d ago First seen · 318 lines · 52 tokens per session scan A d78fa5c19cec
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.
Other skills, from other repositories
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…
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…
memory-capture
Capture decisions, learnings, patterns, and context as persistent memories that survive across sessions.
memory-recall
Search and surface relevant memories to inform current work with decisions, patterns, and learnings from past sessions.
subcog-integrator
Analyze and enhance AI prompts, skills, commands, hooks, and system configurations to leverage Subcog's persistent memory system effectively.
rawq
Context retrieval engine. Semantic + lexical hybrid search over codebases. Returns ranked code chunks with file paths, line ranges, scope labels, and confidence scores.