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-grammargit 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-grammar)<a href="https://agentmods.dev/skills/violetcranberry/coco-search/cocosearch-add-grammar"><img src="https://agentmods.dev/badge/skills/violetcranberry/coco-search/cocosearch-add-grammar/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-grammar"><img src="https://agentmods.dev/badge/skills/violetcranberry/coco-search/cocosearch-add-grammar.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 | $0.03666 |
| Opus 5.5 | $0.00023 | $0.01466 |
| Sonnet 5.5 | $0.00011 | $0.00733 |
| Haiku 4.5 | $0.00006 | $0.00367 |
Grade A, and why
cocosearch-add-grammar 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 1mo 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 — 361 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Add Grammar Handler with CocoSearch
A structured workflow for adding a grammar handler to CocoSearch. Grammar handlers provide domain-specific chunking and metadata for files that share a base language extension but have distinct structure (e.g., GitHub Actions workflows are YAML files with a specific schema).
Philosophy: YamlGrammarBase handles the heavy lifting — matches(), extract_metadata(), comment stripping, and the fallback metadata chain are all inherited. Subclasses only implement _has_content_markers(content) for content validation and _extract_grammar_metadata(stripped, text) for grammar-specific metadata. Override matches() only for broad-pattern grammars that need mandatory content checks (like Kubernetes). This skill guides you through designing content validation and metadata extraction.
Reference: docs/adding-languages.md covers grammar handlers alongside language handlers. This skill is the dedicated deep-dive for grammars.
Step 1: Identify the Grammar
Parse the user's request to determine what's being added.
Extract from the request:
- Grammar name: Lowercase hyphenated identifier (e.g.,
github-actions,docker-compose,ansible-playbook) - Base language: The language this grammar extends (e.g.,
yaml,json,toml) - File path patterns: Glob patterns matching file paths (e.g.,
.github/workflows/*.yml,docker-compose*.yml) - Content markers: Strings that distinguish this grammar from other files with the same extension (e.g.,
on:+jobs:for GitHub Actions,apiVersion:+kind:for Kubernetes)
Confirm with user: "I'll add a grammar handler for [grammar] (base: [language]) matching [patterns]. Let me find the best analog."
Step 2: Find the Best Analog
Choose the closest existing grammar handler based on the grammar type:
| Grammar Type | Analog | Why |
|---|---|---|
| CI/CD pipeline (YAML) | github_actions.py or gitlab_ci.py |
Jobs/stages/steps structure |
| Container orchestration (YAML) | docker_compose.py or kubernetes.py |
Services/resources structure |
| Template (YAML/gotmpl) | helm_template.py or helm_values.py |
Template directives + values |
| Kubernetes manifest (YAML) | kubernetes.py |
Content-heavy matching with exclusions |
| Config values (YAML) | helm_values.py |
Comment-based section markers |
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.
- 1mo ago First seen · 361 lines · 57 tokens per session scan A 3d243574251b
cocosearch-add-grammar is a skill published in the GitHub repository VioletCranberry/coco-search (37 stars, last pushed 4d ago), licensed MIT. It adds 57 tokens to every session and 3,666 once invoked, about $0.0002 per session on Opus 5.5. 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…
rawq
Context retrieval engine. Semantic + lexical hybrid search over codebases. Returns ranked code chunks with file paths, line ranges, scope labels, and confidence scores.
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.