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-extractorgit 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-extractor)<a href="https://agentmods.dev/skills/violetcranberry/coco-search/cocosearch-add-extractor"><img src="https://agentmods.dev/badge/skills/violetcranberry/coco-search/cocosearch-add-extractor/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-extractor"><img src="https://agentmods.dev/badge/skills/violetcranberry/coco-search/cocosearch-add-extractor.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 | $0.00057 | $0.03711 |
| Opus 5 | $0.00028 | $0.01855 |
| Sonnet 5 | $0.00011 | $0.00742 |
| Haiku 4.5 | $0.00006 | $0.00371 |
Grade A, and why
cocosearch-add-extractor 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 — 436 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Add Dependency Extractor with CocoSearch
A structured workflow for adding a dependency extractor to CocoSearch. Dependency extractors parse files to build a graph of what-depends-on-what, enabling deps tree, deps impact, get_file_dependencies/get_file_impact MCP tools, and include_deps=True in search results.
Philosophy: Extractors are autodiscovered and lightweight -- they parse one file at a time and emit edges. Module resolvers are optional and translate raw import strings into file paths. This skill guides you through both, with pre-checks that prevent wasted work.
Reference: The existing 8 extractors in src/cocosearch/deps/extractors/ and 4 resolvers in src/cocosearch/deps/resolver.py serve as patterns.
Step 1: Pre-checks
Before writing any code, verify the extractor is viable.
1a. Check If an Extractor Already Exists
search_code(
query="dependency extractor LANGUAGES",
symbol_type="class",
use_hybrid_search=True,
smart_context=True
)
Or check the registry directly:
uv run python -c "from cocosearch.deps.registry import get_all_extractor_language_ids; print(sorted(get_all_extractor_language_ids()))"
Currently registered: cjs, cts, docker-compose, github-actions, go, helm-template, helm-values, js, jsx, mjs, mts, py, terraform, ts, tsx.
If the target language_id is already listed, stop. The extractor exists. Inform the user.
1b. Determine the Language ID
The extractor's LANGUAGES set must match the language_id assigned during indexing:
| Source | language_id comes from | Example |
|---|---|---|
| Standard language | File extension without dot | .py -> py, .go -> go |
| Language handler | handler.SEPARATOR_SPEC.language_name |
hcl, dockerfile, bash |
| Grammar handler | handler.GRAMMAR_NAME |
docker-compose, github-actions, terraform |
Verify the language_id exists in the system:
search_code(
query="LANGUAGE_EXTENSIONS EXTENSIONS language_name GRAMMAR_NAME",
use_hybrid_search=True,
smart_context=True
)
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 · 436 lines · 57 tokens per session scan A 9a8928c6f6de
cocosearch-add-extractor is a skill published in the GitHub repository VioletCranberry/coco-search (37 stars, last pushed today), licensed MIT. It adds 57 tokens to every session and 3,711 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.