Agent skill

Devql Explore First

by bitloops in bitloops/bitloops

Use always before codebase exploration, bug fixing, SWE-bench tasks, locating symbols, files, or tests, or before using rg, grep, sed, find, or source-file reads in a repository.

Apache-2.0Auto-check passedDevelopment

Install Devql Explore First

skills CLI
$ npx skills add bitloops/bitloops --skill devql-explore-first -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install bitloops/bitloops devql-explore-first --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/bitloops/bitloops.git skills-src && mkdir -p .claude/skills && cp -r skills-src/bitloops/src/host/hooks/augmentation/skills/devql-explore-first .claude/skills/devql-explore-first && rm -rf skills-src

Use ~/.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/

Facts

Skill name
devql-explore-first
GitHub stars
243
Token cost
~897 tokens
SKILL.md length
305 words
Files
1
Skills in repo
2
Repo updated
First seen
Licence
Apache-2.0

At a glance

Use always before codebase exploration, bug fixing, SWE-bench tasks, locating symbols, files, or tests, or before using rg, grep, sed, find, or source-file reads in a repository.

  • Tasks that involve Debugging
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Devql Explore First is an agent skill from bitloops/bitloops. Use always before codebase exploration, bug fixing, SWE-bench tasks, locating symbols, files, or tests, or before using rg, grep, sed, find, or source-file reads in a repository.

Its SKILL.md is about 900 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, covering Debugging. It works with Google Gemini and Rust. The repository describes itself as: Give AI coding agents the context they need to ship production-quality software. The licence is Apache-2.0.

When your agent uses it

  • Tasks that involve Debugging

Example prompts

  • “/devql-explore-first”

What it can do on your machine

Read from SKILL.md and the folder at commit dc8980c. It shows what the files ask for, not the result of running them.

  • Tool permissions

    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.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are bash).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Devql Explore First loads about 897 tokens when it runs. Until then it costs about 50 tokens; SKILL.md has 305 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~50
When it runs · the whole SKILL.md, loaded when a task matches
~897

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.

Safety

Auto-check passed

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.

SKILL.md

The full file from bitloops/bitloops at commit dc8980c, republished under its Apache-2.0 licence (© bitloops). 305 words, ~897 tokens.

Download SKILL.mdSave it as .claude/skills/devql-explore-first/SKILL.md (or your agent's skills folder).
name
devql-explore-first
description
Use always before codebase exploration, bug fixing, SWE-bench tasks, locating symbols, files, or tests, or before using rg, grep, sed, find, or source-file reads in a repository.

DevQL Explore First

<VERY_IMPORTANT> For code understanding and exploration, DevQL is the primary discovery tool, not a one-time preflight. Use bitloops devql query ... whenever locating symbols, files, tests, implementations, callers/usages, or the next source region to inspect. </VERY_IMPORTANT>

Do not use sed, rg, grep, find, wc, directory crawling, or broad source-file reads to discover task-relevant code while DevQL can answer the lookup. Use traditional tools only to:

  • read bounded ranges returned by DevQL
  • inspect files you are editing after DevQL selected them
  • run tests or git/status commands
  • fall back when DevQL fails, is empty, or contradicts the task

Do not run bitloops devql --help or bitloops devql query --help.

Choose the most specific selector:

  • known symbolFqn: use symbolFqn
  • known file or file range: use path, optionally with lines
  • single concrete identifier, method name, literal, error code, path-like string, or copied snippet: use searchMode: LEXICAL
  • architecture role terms such as API endpoint, command handler, repository, adapter, or boundary: use searchMode: ARCHITECTURE
  • multiple related terms, behavior, concept, or task keywords without one exact anchor: omit searchMode and use default AUTO

Fuzzy symbol-name lookup is included in the lexical lane; do not use a separate fuzzy selector.

Use compact exploration queries. If the prompt has no concrete anchor, start with the default AUTO query:

bash
bitloops devql query '{ selectArtefacts(by: { search: "<short behavior phrase or task keywords>" }) { count artefacts(first: 10) { path symbolFqn canonicalKind startLine endLine score } } }'
bitloops devql query '{ selectArtefacts(by: { search: "<single identifier, literal, path fragment, or short snippet>", searchMode: LEXICAL }) { count artefacts(first: 10) { path symbolFqn canonicalKind startLine endLine score } } }'
bitloops devql query '{ selectArtefacts(by: { symbolFqn: "<symbol-fqn>" }) { count artefacts(first: 10) { path symbolFqn canonicalKind startLine endLine score } } }'
bitloops devql query '{ selectArtefacts(by: { path: "<repo-relative-path>", lines: { start: <start>, end: <end> } }) { count artefacts(first: 10) { path symbolFqn canonicalKind startLine endLine score } } }'

For architecture role context on a known file, use the minimal GraphQL shape and request role fields only unless target or rule metadata is needed:

bash
bitloops devql query  '{ selectArtefacts(by: { path: "<repo-relative-path>" }) { architectureRoles(first: 10) { items(first: 10) { role { canonicalKey displayName family description } target { symbolFqn canonicalKind } } } } }'
bitloops devql query  '{ selectArtefacts(by: { symbolFqn: "<symbol-fqn>" }) { architectureRoles(first: 10) { items(first: 10) { role { canonicalKey displayName family description } target { symbolFqn canonicalKind } } } } }'

If DevQL returns relevant paths and line ranges:

  • read only about 50 lines before and after those ranges
  • do not duplicate the same search with rg, grep, glob, or find
  • for each new exploration question, query DevQL again instead of switching to grep/glob/find
  • fall back to normal search only if DevQL fails, is empty, or contradicts the task
  • use at most 3 DevQL calls before each bounded source-read phase

© bitloops, 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

Files

Just SKILL.md in bitloops/src/host/hooks/augmentation/skills/devql-explore-first of bitloops/bitloops.

Open the folder on GitHubat commit dc8980c

Compare with similar skills

Devql Explore First 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.

Devql Explore First compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Devql Explore First this skillbitloops/bitloops243—~897Automated safety check: PassApache-2.0
OpenLogi macOS Permissions TriageAprilNEA/OpenLogi23k—~2.5kAutomated safety check: NotesApache-2.0
Debug Tuitrasta298/keifu811—~1.3kAutomated safety check: PassMIT
Cppcrazyguitar/cppcheatsheet290—~1.8kAutomated safety check: PassMIT
Codex TUI Testingopeninterpreter/openinterpreter69k2 repos~133Automated safety check: PassApache-2.0
Dbgtheodo-group/debug-that158—~2.2kAutomated safety check: PassMIT

Similar skills

  • Decides whether an OpenLogi device problem on macOS is a privacy-permission (TCC) problem, using agent log lines, and says which identity needs which grant.

    23k GitHub stars~2.5k tokensUpdated 4 days ago
    DevelopmentAuto-check: notes
  • Debug Tui

    trasta298/keifu

    Drive and debug the real keifu TUI autonomously via its remote-control debug server (--debug-listen) — launch headlessly, inject keys/mouse, dump the rendered screen as text, and inspect app state.

    811 GitHub stars~1.3k tokensUpdated 2 mo ago
    DevelopmentAuto-check passed
  • Cpp

    crazyguitar/cppcheatsheet

    Comprehensive C/C++ programming reference covering everything from C11-C23 and C++11-C++23, system programming, CUDA GPU computing, debugging tools, Rust interop, and advanced topics.

    290 GitHub stars~1.8k tokensUpdated yesterday
    DevelopmentAuto-check passed
  • Codex TUI Testing

    openinterpreter/openinterpreter

    Guide for testing Codex TUI interactively

    69k GitHub starsUsed in 2 repos~133 tokens
    DevelopmentAuto-check passed
  • Dbg

    theodo-group/debug-that

    Debug applications using the dbg CLI debugger. An agent skill from theodo-group/debug-that.

    158 GitHub stars~2.2k tokensUpdated today
    DevelopmentAuto-check passed
  • Issue Tracking

    static-web-server/static-web-server

    Triage, debug, fix, and document issues for the Static Web Server (SWS) project — bug reports, root cause analysis, fix implementation, and regression prevention

    2.4k GitHub stars~1.5k tokensUpdated today
    DevelopmentAuto-check passed

More from bitloops/bitloops

  • Using Devql

    bitloops/bitloops

    A skill your agent uses when answering repo-understanding questions in a Bitloops repo with DevQL guidance enabled, especially when you need to locate code by path, line range, exact symbol, or…

    243 GitHub stars~1.6k tokensUpdated 4 mo ago
    Auto-check passed

Categories

Questions about Devql Explore First

What does Devql Explore First do?

Use always before codebase exploration, bug fixing, SWE-bench tasks, locating symbols, files, or tests, or before using rg, grep, sed, find, or source-file reads in a repository. Devql Explore First is an agent skill from bitloops/bitloops. Use always before codebase exploration, bug fixing, SWE-bench tasks, locating symbols, files, or tests, or before using rg, grep, sed, find, or source-file reads in a repository.

When should I use Devql Explore First?

Devql Explore First fits situations like: tasks that involve Debugging.

How do I install Devql Explore First in Claude Code?

Run `npx skills add bitloops/bitloops --skill devql-explore-first -a claude-code`. Or copy the skill folder (bitloops/src/host/hooks/augmentation/skills/devql-explore-first in bitloops/bitloops) into .claude/skills/devql-explore-first in your project. Claude Code loads it when a task matches its description.

How do I install Devql Explore First in Codex?

Run `npx skills add bitloops/bitloops --skill devql-explore-first -a codex`. Or copy the skill folder (bitloops/src/host/hooks/augmentation/skills/devql-explore-first in bitloops/bitloops) into .agents/skills/devql-explore-first in your project. Codex loads it when a task matches its description.

Can I use Devql Explore First in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add bitloops/bitloops --skill devql-explore-first -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/devql-explore-first, .gemini/skills/devql-explore-first, .github/skills/devql-explore-first and .opencode/skills/devql-explore-first in your project.

What does Devql Explore First need to run?

SKILL.md names no scripts, command-line tools or credentials: Devql Explore First is instructions for the agent only.

Does Devql Explore First access the network?

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.

Is Devql Explore First safe to install?

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.

What licence does Devql Explore First use?

Devql Explore First 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.

How many tokens does Devql Explore First use?

About 897 tokens (SKILL.md is roughly 3.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Devql Explore First?

Skills that share tags, products or a category with Devql Explore First: OpenLogi macOS Permissions Triage (AprilNEA/OpenLogi, 23k stars), Debug Tui (trasta298/keifu, 811 stars), Cpp (crazyguitar/cppcheatsheet, 290 stars) and Codex TUI Testing (openinterpreter/openinterpreter, 69k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Devql Explore First?

bitloops (a GitHub organization) maintains it in bitloops/bitloops, which has 243 GitHub stars. The repository holds 2 skills in this directory. The repository was last updated on June 1, 2026.

Source: bitloops/bitloops on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.