Vercel Composition Patterns
supabase/supabase
React composition patterns that scale. An agent skill from supabase/supabase.
Build, review, and explain agdb queries accurately. An agent skill from agnesoft/agdb.
$ npx skills add agnesoft/agdb --skill agdb-query -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install agnesoft/agdb agdb-query --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/agnesoft/agdb.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.github/skills/agdb-query .claude/skills/agdb-query && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "agdb-query" agent skill from https://github.com/agnesoft/agdb/tree/main/.github/skills/agdb-query into .claude/skills/agdb-query/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agdb-query", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/agnesoft/agdb/tree/main/.github/skills/agdb-queryType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add agnesoft/agdb --skill agdb-query -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install agnesoft/agdb agdb-query --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/agnesoft/agdb.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.github/skills/agdb-query .agents/skills/agdb-query && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "agdb-query" agent skill from https://github.com/agnesoft/agdb/tree/main/.github/skills/agdb-query into .agents/skills/agdb-query/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agdb-query", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add agnesoft/agdb --skill agdb-query -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install agnesoft/agdb agdb-query --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/agnesoft/agdb.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.github/skills/agdb-query .cursor/skills/agdb-query && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "agdb-query" agent skill from https://github.com/agnesoft/agdb/tree/main/.github/skills/agdb-query into .cursor/skills/agdb-query/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agdb-query", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/agnesoft/agdb.git --path .github/skills/agdb-query--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add agnesoft/agdb --skill agdb-query -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install agnesoft/agdb agdb-query --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/agnesoft/agdb.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.github/skills/agdb-query .gemini/skills/agdb-query && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "agdb-query" agent skill from https://github.com/agnesoft/agdb/tree/main/.github/skills/agdb-query into .gemini/skills/agdb-query/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agdb-query", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install agnesoft/agdb agdb-queryInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add agnesoft/agdb --skill agdb-query -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/agnesoft/agdb.git skills-src && mkdir -p .github/skills && cp -r skills-src/.github/skills/agdb-query .github/skills/agdb-query && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "agdb-query" agent skill from https://github.com/agnesoft/agdb/tree/main/.github/skills/agdb-query into .github/skills/agdb-query/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agdb-query", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add agnesoft/agdb --skill agdb-query -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install agnesoft/agdb agdb-query --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/agnesoft/agdb.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.github/skills/agdb-query .opencode/skills/agdb-query && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "agdb-query" agent skill from https://github.com/agnesoft/agdb/tree/main/.github/skills/agdb-query into .opencode/skills/agdb-query/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agdb-query", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
agdb-queryBuild, review, and explain agdb queries accurately. An agent skill from agnesoft/agdb.
Agdb Query is an agent skill from agnesoft/agdb. Build, review, and explain agdb queries accurately. Use this skill when writing QueryBuilder chains, converting between search/select/insert/remove, reasoning about where conditions, or debugging query logic and result semantics in agdb.
Its SKILL.md is about 4.4k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Development. The repository describes itself as: Agnesoft Graph Database. The licence is Apache-2.0.
6 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit 0d70098. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
No scripts in the folder and no shell commands in SKILL.md (its code samples are rust).
From the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Agdb Query loads about 4.4k tokens when it runs. Until then it costs about 62 tokens; SKILL.md has 1,007 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from agnesoft/agdb at commit 0d70098, republished under its Apache-2.0 licence (© agnesoft). 1,007 words, ~4,369 tokens.
.claude/skills/agdb-query/SKILL.md (or your agent's skills folder).Use this skill when working with agdb query construction and behavior, especially:
search + where_ conditions and modifiersinsert / remove / select / searchQueryResult and DbType mappinginsert().amend(), remove().amend(), insert().amend_or(), etc.)Primary sources in this repository:
agdb/src/query.rsagdb/src/query_builder.rsagdb/src/query_builder/*agdb/src/query/*agdb_web/content/docs/03.references/01.queries.mdQueryBuilder builds typed query objects.Db::exec (immutable) or Db::exec_mut (mutable).Result<QueryResult, DbError>.QueryResult contains:result: numeric aggregate (count or similar)elements: element payloads (ids and/or values depending on query, always present, can be empty)QueryResult::ids() extracts just the DbId of every element — useful for chaining.QueryResult implements TryInto<Vec<T>> and TryInto<T> for DbType/DbElement types.exec for immutable queries: select, search.exec_mut for mutable queries: insert, remove.transaction / transaction_mut) are for grouping multiple queries.Transaction/TransactionMut with the same exec/exec_mut methods.exec)// Select all values by id
QueryBuilder::select().ids(1).query();
// Select specific keys
QueryBuilder::select().values(["k".into()]).ids([1, 2]).query();
// Select keys only (no values)
QueryBuilder::select().keys().ids([1, 2]).query();
// Select key count
QueryBuilder::select().key_count().ids([1, 2]).query();
// Select edge count (from/to/both)
QueryBuilder::select().edge_count_from().ids(1).query();
QueryBuilder::select().edge_count_to().ids(1).query();
QueryBuilder::select().edge_count().ids(1).query();
// Select aliases
QueryBuilder::select().aliases().ids(1).query();
QueryBuilder::select().aliases().query(); // all aliases
// Select indexes
QueryBuilder::select().indexes().query();
// Select node count
QueryBuilder::select().node_count().query();
// Search - BFS (default) from alias
QueryBuilder::search().from("alias").query();
// Search - path search (A*)
QueryBuilder::search().from(1).to(2).query();
// Search - index lookup (fastest for single-key equality)
QueryBuilder::search().index("username").value("alice").query();
// Search - full element scan
QueryBuilder::search().elements().query();
// Nested: select values via search result
QueryBuilder::select().search().from("alias").where_().node().query();
// Nested: typed select (single result, limit=1)
QueryBuilder::select().element::<User>().search().from("alias").where_().key("name").value("Alice").query();
// Nested: typed select (all matches)
QueryBuilder::select().elements::<User>().search().from("alias").where_().node().query();exec_mut)// Insert nodes
QueryBuilder::insert().nodes().count(1).query();
QueryBuilder::insert().nodes().aliases(["root"]).query();
QueryBuilder::insert().nodes().values(&typed_vec).query();
// Upsert (insert or update): pass existing ids
QueryBuilder::insert().nodes().ids(existing_ids).values(&typed_vec).query();
// Insert edges
QueryBuilder::insert().edges().from(1).to(2).query();
QueryBuilder::insert().edges().from("alias_a").to([3, 4, 5]).query();
QueryBuilder::insert().edges().from(1).to(2).values([[("weight", 10).into()]]).query();
// Insert/update aliases
QueryBuilder::insert().aliases(["name"]).ids(1).query();
// Insert/update values
QueryBuilder::insert().values([vec![("k", 1).into()]]).ids(1).query();
QueryBuilder::insert().values_uniform([("k", 1).into()]).ids(1).query();
// Insert single typed element (DbElement)
QueryBuilder::insert().element(typed_element).query();
// Insert multiple typed elements (DbElement)
QueryBuilder::insert().elements(&typed_elements).query();
// Create index
QueryBuilder::insert().index("key").query();
// Remove elements
QueryBuilder::remove().ids([1, 2]).query();
// Remove aliases (not the elements)
QueryBuilder::remove().aliases("name").query();
// Remove specific properties
QueryBuilder::remove().values("key").ids(1).query();
// Remove index
QueryBuilder::remove().index("key").query();Amendment operations modify existing values in place rather than replacing them:
// Add to numeric value (saturating), append to string/vec
QueryBuilder::insert().amend([vec![("score", 10).into()]]).ids(1).query();
// Same value applied uniformly to multiple elements
QueryBuilder::insert().amend_uniform([("score", 10).into()]).ids([1, 2]).query();
// Subtract from numeric value, remove first occurrence from string/vec
QueryBuilder::remove().amend([vec![("tags", "old_tag").into()]]).ids(1).query();
// Bitwise operations on integer/byte values
QueryBuilder::insert().amend_or([vec![("flags", 0x04_u64).into()]]).ids(1).query();
QueryBuilder::insert().amend_and([vec![("mask", 0xFF_u64).into()]]).ids(1).query();
QueryBuilder::insert().amend_xor([vec![("toggle", 0x01_u64).into()]]).ids(1).query();
// Uniform variants: amend_or_uniform, amend_and_uniform, amend_xor_uniformamend (add) behavior by type:
| Type | Behavior |
|---|---|
I64, U64 | Saturating addition |
F64 | Floating-point addition |
String | Concatenation |
Bytes | Byte vector extension |
Vec* | Extend with elements (or push single scalar) |
remove().amend() behavior by type:
| Type | Behavior |
|---|---|
I64, U64 | Saturating subtraction |
F64 | Floating-point subtraction |
String | Remove first occurrence of substring |
Bytes | Not supported (returns error) |
Vec* | Remove first matching element per item |
QueryBuilder::search() defaults to breadth-first search.QueryBuilder::select().search() is shorthand for selecting values via a nested search query.QueryBuilder::insert().values(...).search() is shorthand for using search result ids as insert targets.QueryBuilder::insert().nodes().ids(...) enables insert-or-update semantics:QueryBuilder::insert().edges().ids(...) does the same for edges (updates values of found edge ids).QueryBuilder::select().element::<T>() sets limit = 1 and uses T::db_keys().T::db_element_id() is Some, typed select/search adds a db_element_id filter automatically.QueryBuilder::insert().element(x) and elements(&xs) only work with types implementing DbElement (not just DbType).search().depth_first() changes traversal to DFS — more efficient when searching for a single item.where_) guidanceCondition chains compile into QueryCondition items with:
And or OrNone, Not, Beyond, NotBeyond.where_().node()
.where_().edge()
.where_().key("k").value(1)
.where_().keys(["k1".into(), "k2".into()])
.where_().distance_less_than_or_equal(2)
.where_().ids([1, 2, 3]).where_().node().or().edge()
.where_().node().and().key("k").value("v")
.where_().node().or().where_().edge().and().key("k").value(1).end_where()Important: or() passes if either side evaluates to true. and() passes only if both sides evaluate to true.
not(): negates selection result of the next condition.beyond(): controls traversal only; continue past an element only if condition passes.not_beyond(): controls traversal only; stop past an element if condition passes.Important: beyond() / not_beyond() do not directly select/reject elements by themselves. Pair them with normal selection conditions when needed.
Distance shorthands — avoid manually constructing CountComparison:
.where_().distance_less_than(3) // same as .distance(CountComparison::LessThan(3))
.where_().distance_less_than_or_equal(3)
.where_().distance_greater_than(1)
.where_().distance_greater_than_or_equal(1)
.where_().distance_not_equal(0)
.where_().neighbor() // shorthand for distance == 2Value comparison shorthands — avoid manually constructing Comparison:
.where_().key("age").greater_than(18) // same as .value(Comparison::GreaterThan(18.into()))
.where_().key("age").greater_than_or_equal(18)
.where_().key("age").less_than(65)
.where_().key("age").less_than_or_equal(65)
.where_().key("name").not_equal("admin")
.where_().key("name").contains("alice") // substring/element match
.where_().key("name").starts_with("user_")
.where_().key("name").ends_with("_admin")
.where_().key("role").any(["admin", "mod"]) // matches if value is any of the list
.where_().key("name").regex("^user_\\d+$") // regex match on string valuesEdge count shorthands — avoid manually constructing CountComparison:
.where_().edge_count_from_greater_than(0) // has outgoing edges
.where_().edge_count_to_less_than(5) // fewer than 5 incoming edges
// also: edge_count_*, edge_count_from_*, edge_count_to_* with _less_than, _greater_than, _not_equal, etc.Typed element filter:
where_().element::<T>():db_element_id filter if availablewhere_().ids(...) does not support nested search ids in this condition context; a search passed there is ignored.from(x): forward traversal (starting from x)to(x): reverse traversal following incoming edges (starting from x)from(x).to(y): path search (A*) going from x to yto(y).from(x): reverse path search — follows incoming edges, can be significantly faster when the destination has fewer incoming edges than the origin has outgoingelements(): full element scan (can be expensive)index("key").value(v): indexed lookup — supports limit, offset, order_by, and where_() conditions just like graph searchesSearch supports breadth-first (BFS, default) and depth-first (DFS, depth_first()) traversal order, can be selected in the builder query (QueryBuilder::search().depth_first()...).
This changes order in which the elements are visited and therefore the order of results and how beyond/not_beyond conditions are applied.
Use limit and offset for large traversals. For elements() queries, always consider limit first.
You can also order results with order_by:
QueryBuilder::search().from("root").order_by([DbKeyOrder::Asc("name".into())]).query();searchselect (optionally with nested search)insertremovePitfall: using exec with mutable query.
exec_mut.Pitfall: insert().values(Multi) count does not match target ids.
values_uniform.Pitfall: expecting search to return full values.
select().search()... when values are needed.Pitfall: forgetting .query() at end of builder chain.
.query() before execution.Pitfall: mixing traversal control with selection logic.
beyond/not_beyond for traversal and add explicit node/edge/key conditions for selection.Pitfall: using element() (singular) when expecting multiple results.
elements::<T>() (plural) for multiple matches. element::<T>() sets limit = 1.Pitfall: constructing queries as raw JSON via curl or HTTP client.
QueryBuilder in Rust. The query serialization format has deeply nested enums that are not designed for manual construction. Use the agdb_api client SDK instead.Pitfall: expecting amend on incompatible types to silently no-op.
DbError when types don't match (e.g. adding I64 to String). Ensure the stored value type matches the amendment value type.When generating query code:
QueryResult.result meaning.DbType), call out required keys and optional db_id behavior.let q = QueryBuilder::select()
.elements::<User>()
.search()
.index("username")
.value("alice")
.query();
let result = db.exec(q)?;
let users: Vec<User> = result.try_into()?;let q = QueryBuilder::insert()
.values_uniform([("active", 1).into()])
.ids(42)
.query();
db.exec_mut(q)?;let q = QueryBuilder::search()
.from("root")
.where_()
.beyond()
.key("role")
.value("admin")
.query();
let ids = db.exec(q)?.ids();db.transaction_mut(|t| {
let root = t.exec_mut(
QueryBuilder::insert().nodes().aliases(["users"]).query()
)?;
let users = t.exec_mut(
QueryBuilder::insert().nodes().values(&user_data).query()
)?;
t.exec_mut(
QueryBuilder::insert().edges().from("users").to(users).query()
)
})?;db.exec_mut(
QueryBuilder::insert()
.amend([vec![("visit_count", 1_i64).into()]])
.ids("page_home")
.query()
)?;let result = db.exec(
QueryBuilder::select()
.search()
.depth_first()
.from("user")
.where_()
.keys("role")
.or()
.keys("name")
.query(),
)?;
// DFS guarantees: edge (id < 0) followed by its target node (id > 0)
for element in result.elements {
if element.id.0 < 0 {
// edge — extract relationship properties
} else {
// node — extract entity properties
}
}use agdb::{DbType, QueryBuilder};
use agdb_api::{AgdbApi, ReqwestClient, DbKind};
#[derive(Debug, DbType)]
struct User {
username: String,
email: String,
}
#[tokio::main]
async fn main() -> anyhow::Result<()> {
let mut client = AgdbApi::new(ReqwestClient::new(), "localhost:3000");
client.user_login("admin", "admin").await?;
client.db_add("admin", "my_db", DbKind::Mapped).await?;
// Create root + users + edges in one atomic call
let users = vec![
User { username: "alice".into(), email: "a@b.com".into() },
User { username: "bob".into(), email: "b@b.com".into() },
];
let results = client.db_exec_mut("admin", "my_db", &[
QueryBuilder::insert().nodes().aliases(["users"]).query().into(),
QueryBuilder::insert().nodes().values(&users).query().into(),
]).await?.1;
client.db_exec_mut("admin", "my_db", &[
QueryBuilder::insert().edges().from("users").to(results[1].ids()).query().into(),
QueryBuilder::insert().index("username").query().into(),
]).await?;
// Query back
let (_, results) = client.db_exec("admin", "my_db", &[
QueryBuilder::select()
.elements::<User>()
.search()
.index("username")
.value("alice")
.query()
.into(),
]).await?;
let found: Vec<User> = results[0].clone().try_into()?;
println!("{found:?}");
Ok(())
}insert/remove/select/search)exec vs exec_mut).query() present.into() present when batching queries in a VecMulti vs Single values shape correcttry_into) matches selected keysQueryBuilder© agnesoft, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Just SKILL.md in .github/skills/agdb-query of agnesoft/agdb.
Open the folder on GitHubat commit 0d70098
Agdb Query next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Agdb Query this skillagnesoft/agdb | 143 | — | ~4.4k | Automated safety check: Pass | Apache-2.0 | |
| Vercel Composition Patternssupabase/supabase | 111k | 59 repos | ~726 | Automated safety check: Pass | MIT | |
| Finishing a Development Branchobra/superpowers | 296k | 5 repos | ~1.9k | Automated safety check: Pass | MIT | |
| Typescript Advanced Typesrolling-scopes/rsschool-app | 10k | 25 repos | ~4.2k | Automated safety check: Pass | MPL-2.0 | |
| PR Babysitteropeninterpreter/openinterpreter | 69k | 3 repos | ~4.2k | Automated safety check: Pass | Apache-2.0 | |
| Code Review ChecklistshareAI-lab/learn-claude-code | 78k | 5 repos | ~1.1k | Automated safety check: Pass | MIT |
supabase/supabase
React composition patterns that scale. An agent skill from supabase/supabase.
obra/superpowers
Walks the last step of a branch: confirm tests pass, detect the git environment, ask how to integrate, carry out your choice and clean up the worktree.
rolling-scopes/rsschool-app
Master TypeScript's advanced type system including generics, conditional types, mapped types, template literals, and utility types for building type-safe applications.
openinterpreter/openinterpreter
Watches an open GitHub pull request until it merges, handling review comments, diagnosing CI failures and retrying flaky checks along the way.
shareAI-lab/learn-claude-code
Reviews code against a five-part checklist covering security, correctness, performance, maintainability and testing, and reports findings in a fixed format.
onyx-dot-app/onyx
Iteratively improves a PR (GitHub), MR (GitLab), or shelved changelist (Perforce) until Greptile gives it a 5/5 confidence score with zero unresolved comments.
agnesoft/agdb
Install PHP and Composer, verify they are available in PATH, and confirm the PHP tooling required by this repository works.
agnesoft/agdb
Navigate agdb API structure, endpoints, authentication, and client libraries.
Categories
Build, review, and explain agdb queries accurately. An agent skill from agnesoft/agdb. Agdb Query is an agent skill from agnesoft/agdb. Build, review, and explain agdb queries accurately.
Agdb Query fits situations like: writing QueryBuilder chains; converting between search/select/insert/remove; reasoning about where conditions; debugging query logic and result semantics in agdb.
Run `npx skills add agnesoft/agdb --skill agdb-query -a claude-code`. Or copy the skill folder (.github/skills/agdb-query in agnesoft/agdb) into .claude/skills/agdb-query in your project. Claude Code loads it when a task matches its description.
Run `npx skills add agnesoft/agdb --skill agdb-query -a codex`. Or copy the skill folder (.github/skills/agdb-query in agnesoft/agdb) into .agents/skills/agdb-query in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add agnesoft/agdb --skill agdb-query -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/agdb-query, .gemini/skills/agdb-query, .github/skills/agdb-query and .opencode/skills/agdb-query in your project.
SKILL.md names no scripts, command-line tools or credentials: Agdb Query is instructions for the agent only.
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
Agdb Query is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 4.4k tokens (SKILL.md is roughly 17k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Agdb Query: Vercel Composition Patterns (supabase/supabase, 111k stars), Finishing a Development Branch (obra/superpowers, 296k stars), Typescript Advanced Types (rolling-scopes/rsschool-app, 10k stars) and PR Babysitter (openinterpreter/openinterpreter, 69k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
agnesoft (a GitHub user) maintains it in agnesoft/agdb, which has 143 GitHub stars. The repository holds 3 skills in this directory. The repository was last updated on October 6, 2026.
Source: agnesoft/agdb on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.