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-add-languagegit 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-add-language)<a href="https://agentmods.dev/skills/violetcranberry/coco-search/cocosearch-add-language"><img src="https://agentmods.dev/badge/skills/violetcranberry/coco-search/cocosearch-add-language/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/violetcranberry/coco-search/cocosearch-add-language"><img src="https://agentmods.dev/badge/skills/violetcranberry/coco-search/cocosearch-add-language.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00053 | $0.04732 |
| Opus 5 | $0.00026 | $0.02366 |
| Sonnet 5 | $0.00011 | $0.00946 |
| Haiku 4.5 | $0.00005 | $0.00473 |
Grade A, and why
cocosearch-add-language 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 10d 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 — 539 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Add Language Support with CocoSearch
A structured workflow for adding language support to CocoSearch. Navigates up to 6 independent paths (handler, symbol extraction, grammar, context expansion, dependency extraction, documentation) and ensures every registration point is covered.
Philosophy: The most common failure when adding language support is missing a registration step. This skill makes that impossible by tracking every step explicitly.
Reference: docs/adding-languages.md is the authoritative technical guide. This skill wraps it in an interactive workflow.
Step 1: Identify the Language
Parse the user's request to determine what's being added.
Extract from the request:
- Language name: The language or format (e.g., "Kotlin", "Ansible", "Makefile")
- File extensions: What extensions it uses (e.g.,
.kt,.kts) - Desired capabilities: Which paths the user wants (chunking, symbol filtering, context expansion, or all)
Confirm with user: "I'll add support for [language] with extensions [list]. Let me determine which paths apply."
Step 2: Determine Applicable Paths
Check two things to decide which of the 5 paths (A-E) apply:
2a. Check CocoIndex's Built-in Language List
CocoIndex's SplitRecursively has built-in Tree-sitter chunking for ~28 languages. Search for the language mapping:
search_code(
query="LANGUAGE_EXTENSIONS supported languages",
use_hybrid_search=True,
smart_context=True
)
Also check the CocoIndex docs: if the language is in the built-in list, chunking works automatically -- no handler (Path A) needed.
2b. Check tree-sitter-language-pack Support
If the user wants symbol extraction (Path B) or context expansion (Path E), the language must be in tree-sitter-language-pack:
uv run python -c "from tree_sitter_language_pack import SupportedLanguage; print(sorted(SupportedLanguage.__args__))"
Verify a specific language:
uv run python -c "from tree_sitter_language_pack import get_parser; p = get_parser('<language>'); print(p)"
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.
- 10d ago First seen · 539 lines · 53 tokens per session scan A b85c95d4f680
cocosearch-add-language is a skill published in the GitHub repository VioletCranberry/coco-search (37 stars, last pushed today), licensed MIT. It adds 53 tokens to every session and 4,732 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.