Navigator
leewayworks/guochuang-gps
A skill your agent uses when a user asks for a GPS review of a Guochuang project folder or materials, needs track or group routing, or wants a readiness diagnosis and next-step plan.
Explicit-only navigator for the dev-skills workflow. An agent skill from hashgraph-online/awesome-codex-plugins.
Apache-2.0Auto-check passed
Install Dev Auto
$ npx skills add hashgraph-online/awesome-codex-plugins --skill dev-auto -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install hashgraph-online/awesome-codex-plugins dev-auto --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/hashgraph-online/awesome-codex-plugins.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/Jason-chen-coder/dev-skills/skills/dev-auto .claude/skills/dev-auto && 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 "dev-auto" agent skill from https://github.com/hashgraph-online/awesome-codex-plugins/tree/main/plugins/Jason-chen-coder/dev-skills/skills/dev-auto into .claude/skills/dev-auto/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "dev-auto", 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/hashgraph-online/awesome-codex-plugins/tree/main/plugins/Jason-chen-coder/dev-skills/skills/dev-autoType 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 hashgraph-online/awesome-codex-plugins --skill dev-auto -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install hashgraph-online/awesome-codex-plugins dev-auto --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/hashgraph-online/awesome-codex-plugins.git skills-src && mkdir -p .agents/skills && cp -r skills-src/plugins/Jason-chen-coder/dev-skills/skills/dev-auto .agents/skills/dev-auto && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "dev-auto" agent skill from https://github.com/hashgraph-online/awesome-codex-plugins/tree/main/plugins/Jason-chen-coder/dev-skills/skills/dev-auto into .agents/skills/dev-auto/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "dev-auto", 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 hashgraph-online/awesome-codex-plugins --skill dev-auto -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install hashgraph-online/awesome-codex-plugins dev-auto --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/hashgraph-online/awesome-codex-plugins.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/plugins/Jason-chen-coder/dev-skills/skills/dev-auto .cursor/skills/dev-auto && 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 "dev-auto" agent skill from https://github.com/hashgraph-online/awesome-codex-plugins/tree/main/plugins/Jason-chen-coder/dev-skills/skills/dev-auto into .cursor/skills/dev-auto/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "dev-auto", 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/hashgraph-online/awesome-codex-plugins.git --path plugins/Jason-chen-coder/dev-skills/skills/dev-auto--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 hashgraph-online/awesome-codex-plugins --skill dev-auto -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install hashgraph-online/awesome-codex-plugins dev-auto --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/hashgraph-online/awesome-codex-plugins.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/plugins/Jason-chen-coder/dev-skills/skills/dev-auto .gemini/skills/dev-auto && 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 "dev-auto" agent skill from https://github.com/hashgraph-online/awesome-codex-plugins/tree/main/plugins/Jason-chen-coder/dev-skills/skills/dev-auto into .gemini/skills/dev-auto/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "dev-auto", 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 hashgraph-online/awesome-codex-plugins dev-autoInstalls 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 hashgraph-online/awesome-codex-plugins --skill dev-auto -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/hashgraph-online/awesome-codex-plugins.git skills-src && mkdir -p .github/skills && cp -r skills-src/plugins/Jason-chen-coder/dev-skills/skills/dev-auto .github/skills/dev-auto && 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 "dev-auto" agent skill from https://github.com/hashgraph-online/awesome-codex-plugins/tree/main/plugins/Jason-chen-coder/dev-skills/skills/dev-auto into .github/skills/dev-auto/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "dev-auto", 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 hashgraph-online/awesome-codex-plugins --skill dev-auto -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install hashgraph-online/awesome-codex-plugins dev-auto --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/hashgraph-online/awesome-codex-plugins.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/plugins/Jason-chen-coder/dev-skills/skills/dev-auto .opencode/skills/dev-auto && 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 "dev-auto" agent skill from https://github.com/hashgraph-online/awesome-codex-plugins/tree/main/plugins/Jason-chen-coder/dev-skills/skills/dev-auto into .opencode/skills/dev-auto/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "dev-auto", 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.
Facts
- Skill name
dev-auto- GitHub stars
- 1.2k
- Token cost
- ~1.8k tokens
- SKILL.md length
- 894 words
- Files
- 4 (incl. references)
- Skills in repo
- 686
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Explicit-only navigator for the dev-skills workflow. An agent skill from hashgraph-online/awesome-codex-plugins.
- The user names dev-auto
- SKILL.md covers Scope and modes, Resolve the work item, Interpret evidence and Choose the next step, plus 3 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
- Explicitly asks for workflow guidance across requirements
What it does
Dev Auto is an agent skill from hashgraph-online/awesome-codex-plugins. Explicit-only navigator for the dev-skills workflow. Use when the user names dev-auto or explicitly asks for workflow guidance across requirements, implementation, verification, and delivery. Recommends the next step from current evidence; does not execute the workflow. Generic implementation requests or an isolated "what next" do not trigger it. Supports [slug], --status, --next, and --recover.
Its SKILL.md is about 1.8k tokens, which your agent loads only when the skill is triggered. The skill folder holds 5 other files, including reference files (for example `agents/openai.yaml`, `examples.md` and `references/dev-baseline.md`).
The repository describes itself as: A curated list of awesome OpenAI Codex / ChatGPT plugins, skills, and resources. The 1 Codex Marketplace. See live plugins at: https://hol.org/plugins/best-codex-plugins. The licence is Apache-2.0.
When your agent uses it
- The user names dev-auto
- Explicitly asks for workflow guidance across requirements
Example prompts
- “what next”
- “/dev-auto”
What it can do on your machine
Read from SKILL.md and the folder at commit 78497e5. 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.
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
Dev Auto loads about 1.8k tokens when it runs, and up to ~2.7k if it reads all its reference files. Until then it costs about 102 tokens; SKILL.md has 894 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.
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 hashgraph-online/awesome-codex-plugins at commit 78497e5, republished under its Apache-2.0 licence (© hashgraph-online). 894 words, ~1,799 tokens.
Download SKILL.mdSave it as
.claude/skills/dev-auto/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.- name
- dev-auto
- description
- Explicit-only navigator for the dev-skills workflow. Use when the user names dev-auto or explicitly asks for workflow guidance across requirements, implementation, verification, and delivery. Recommends the next step from current evidence; does not execute the workflow. Generic implementation requests or an isolated "what next" do not trigger it. Supports [slug], --status, --next, and --recover.
Dev Auto
Recommend the shortest useful path through dev-skills from the user's current state. This is a read-only navigator: no code, artifact writes, subagents, or automatic skill invocation.
Read references/dev-baseline.md. Resolve project paths against the user's project, not the installed skill directory.
Scope and modes
Use only for explicit workflow guidance. A request to fix, implement, plan, review, or commit directly belongs to that task; do not turn it into navigation. When the user has already authorized execution, this optional navigator must not replace that execution request with a suggestion-only response.
| Argument | Output |
|---|---|
[slug] or default | Current evidence, useful remaining steps, and the next action |
--status [slug] | Current state and uncertainty only |
--next [slug] | One next command and one sentence explaining why |
--recover [slug] | Failure cause or missing evidence, recovery action, and what will establish recovery |
Resolve the work item
Use the explicit slug, current conversation, and related artifact names. designs/<slug>.md and plans/<slug>.md describe one feature; fixes/<slug>.md is a separate bug namespace. Count matched feature records once. A matching slug across namespaces is not an error: use the request or source links to distinguish them.
Read .design-context.md and .claude/artifacts/{designs,plans,fixes}/ only as needed. Start with filenames, status, and source metadata; read relevant acceptance criteria, open questions, or review evidence when metadata cannot justify the recommendation. Do not infer completion from file existence or timestamps alone.
Infer an unambiguous current item without a confirmation turn. If several unrelated items remain plausible and the choice changes the answer, ask which item. For a new request, a descriptive proposed slug needs no approval because this skill writes no files.
Interpret evidence
| Evidence | Meaning |
|---|---|
| No artifact | No recorded artifact; work may still exist in code or the conversation |
Spec DRAFT | Intent recorded; check unresolved decisions before recommending implementation |
Spec ALIGNED | Intent aligned; use scope and risk to decide whether a separate plan adds value |
Spec IMPLEMENTED | Implementation recorded; verification and review still require evidence |
Spec STUCK | Named blockers remain; resolve the affected scope before implementation |
Plan APPROVED | Reviewed plan; not evidence that code or tests are complete |
Plan DRAFT / REVISE / REJECT / BELOW_CONSENSUS_THRESHOLD | Inspect the unresolved issue; recommend planning recovery where it matters |
Fix FIXED | Recorded fix; current verification may still be required |
Fix DIAGNOSED | Cause established; implement only if a fix is requested |
Fix PARTIALLY_VERIFIED | Inspect the missing proof; narrow claims or complete the relevant check |
Fix BLOCKED | Resolve the named missing decision or evidence for the affected scope |
Fix BELOW_CONFIDENCE_THRESHOLD | More diagnostic evidence needed |
Fix NEEDS_DESIGN_CHANGE | Plan the required design change, then return to the bug workflow |
| Missing or unknown status | State uncertainty; use available contents and conversation, without inventing a phase |
User-provided recent evidence can establish progress, but qualify what has not been inspected. Do not claim to have verified code from metadata.
Show full SKILL.md (434 more words)Show less
Choose the next step
| Actual need | Recommendation |
|---|---|
| Establish reusable visual direction, with important gaps | dev-design-context; an absent file alone is not a blocker |
| Clarify feature behavior, scope, or acceptance | dev-grill-docs (dev-spec remains the spec-only compatibility alias) |
| Plan known scope with meaningful dependencies or tradeoffs | dev-plan; use --deliberate for material migration, compatibility, security, or recovery risk |
| Implement a scoped feature or refactor | dev-tdd |
| Diagnose or fix broken behavior | dev-fix; it owns the bug regression loop |
| Substantiate completion claims | dev-verify |
| Review pending changes before delivery | dev-code-review |
| Only compose a commit message | dev-commit-writer |
| Finish verified work through requested merge / PR / keep / discard | dev-finish |
These are conditional steps, not a mandatory chain. A precise small change can skip intake and planning. Urgency does not determine risk: recommend a focused bug or implementation path and retain the checks warranted by the actual change. A bug does not need a second TDD workflow after dev-fix.
If workspace choice affects the next action, inspect Git root, branch, and status. Preserve the user's selected checkout and dirty changes. Suggest isolation only when it resolves a concrete conflict; do not add a blanket worktree approval checkpoint.
Recovery
Read the reported failure and relevant evidence before choosing recovery. Ask for missing output only when it is necessary and unavailable locally.
- Requirement blocker: identify the unresolved decision and resume intake when its answer is available.
- Plan feedback: revise affected steps or assumptions. Exhausted review rounds do not prove an architecture change is necessary.
- Failing regression proof: improve the reproduction or assertion before changing more code.
- Repeated fix failure: collect discriminating evidence and revise the hypothesis; consider design work only with supporting evidence.
- Verification or review failure: fix the concrete blocker and rerun affected checks. A confirmed transient environment failure can justify the same command after the environment recovers.
- Missing evidence: add the check or narrow the claim. Do not call it verified or recommend bypassing a blocking finding.
- Destructive finish action: preserve the delivery skill's explicit authorization boundary.
Keep the response proportional to the chosen mode. Link relevant artifacts and give precise skill arguments when those skills are installed; otherwise describe the next task without pretending a missing command exists. See examples.md for edge cases.
SDD Contract
Use existing spec, plan, and fix records as evidence for the recommendation. Preserve their source links, scope, acceptance criteria, and unresolved blockers. Navigation does not change their status or grant implementation or delivery authorization.
Multi-Agent Note
Main-agent-first. This skill does not delegate. A recommended downstream task may delegate under its own rules. In the source repository, docs/multi-agent-policy.md provides optional team context; it is not required for standalone installation.
© hashgraph-online, 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
SKILL.md and 3 other files (references) in plugins/Jason-chen-coder/dev-skills/skills/dev-auto of hashgraph-online/awesome-codex-plugins.
- SKILL.md
- agents/openai.yaml
- examples.md
- references/dev-baseline.md
Open the folder on GitHubat commit 78497e5
Compare with similar skills
Dev Auto 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 |
|---|---|---|---|---|---|---|
| Dev Auto this skillhashgraph-online/awesome-codex-plugins | 1.2k | — | ~1.8k | Automated safety check: Pass | Apache-2.0 | |
| Navigatorleewayworks/guochuang-gps | 106 | — | ~1.3k | Automated safety check: Pass | MIT | |
| Breadcrumb Navigationthedaviddias/Front-End-Checklist | 74k | — | ~418 | Automated safety check: Pass | MIT | |
| Navigation Landmarkthedaviddias/Front-End-Checklist | 74k | — | ~417 | Automated safety check: Pass | MIT | |
| Keyboard Navigationthedaviddias/Front-End-Checklist | 74k | — | ~567 | Automated safety check: Pass | MIT | |
| Skip Navigationthedaviddias/Front-End-Checklist | 74k | — | ~443 | Automated safety check: Pass | MIT |
Similar skills
Breadcrumb Navigation
thedaviddias/Front-End-Checklist
A skill your agent uses when reviewing templates, rendered HTML, or shared components related to Implement accessible breadcrumb navigation.
Navigation Landmark
thedaviddias/Front-End-Checklist
A skill your agent uses when reviewing templates, rendered HTML, or shared components related to Use navigation landmark regions.
Keyboard Navigation
thedaviddias/Front-End-Checklist
A skill your agent uses when reviewing rendered HTML, interactive components, or design-system patterns related to Enable keyboard navigation for all elements.
Skip Navigation
thedaviddias/Front-End-Checklist
A skill your agent uses when reviewing rendered HTML, interactive components, or design-system patterns related to Include a skip navigation link.
Monorepo Navigator
alirezarezvani/claude-skills
Navigate, manage, and optimize monorepos. An agent skill from alirezarezvani/claude-skills.
More from hashgraph-online/awesome-codex-plugins
All 686 skills in this repoAnime Reaction Gif
hashgraph-online/awesome-codex-plugins
Create original anime-style reaction stickers as looping GIFs and MP4 previews, using generated character pose sheets and timed key poses.
Calibredb
hashgraph-online/awesome-codex-plugins
Manage and query Calibre libraries with the calibredb CLI (local paths or Calibre Content server URLs).
Rust API Test Harness
hashgraph-online/awesome-codex-plugins
A skill your agent uses when adding, changing, testing, or debugging Rust HTTP APIs and services, especially when Codex needs black-box integration tests, random-port app startup, real database test…
Art
hashgraph-online/awesome-codex-plugins
Make a studio's game look like something at build time — a cover from a real frame of the game (free), painted covers, backdrops, textures and character plates from image models through the…
Game Balance Economy
hashgraph-online/awesome-codex-plugins
Balance game difficulty, resources, rewards, probability, progression, economies, and dominant strategies.
Manuscript Engagement Analytics
hashgraph-online/awesome-codex-plugins
Analyze nonfiction manuscripts for reader engagement signals, including heading-level word counts, slow starts, long slogs, weak takeaway titles, value pacing, beta-reader comment dropoff, and…
Questions about Dev Auto
What does Dev Auto do?
Explicit-only navigator for the dev-skills workflow. An agent skill from hashgraph-online/awesome-codex-plugins. Dev Auto is an agent skill from hashgraph-online/awesome-codex-plugins. Explicit-only navigator for the dev-skills workflow.
When should I use Dev Auto?
Dev Auto fits situations like: the user names dev-auto; explicitly asks for workflow guidance across requirements.
How do I install Dev Auto in Claude Code?
Run `npx skills add hashgraph-online/awesome-codex-plugins --skill dev-auto -a claude-code`. Or copy the skill folder (plugins/Jason-chen-coder/dev-skills/skills/dev-auto in hashgraph-online/awesome-codex-plugins) into .claude/skills/dev-auto in your project. Claude Code loads it when a task matches its description.
How do I install Dev Auto in Codex?
Run `npx skills add hashgraph-online/awesome-codex-plugins --skill dev-auto -a codex`. Or copy the skill folder (plugins/Jason-chen-coder/dev-skills/skills/dev-auto in hashgraph-online/awesome-codex-plugins) into .agents/skills/dev-auto in your project. Codex loads it when a task matches its description.
Can I use Dev Auto 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 hashgraph-online/awesome-codex-plugins --skill dev-auto -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/dev-auto, .gemini/skills/dev-auto, .github/skills/dev-auto and .opencode/skills/dev-auto in your project.
What does Dev Auto need to run?
SKILL.md names no scripts, command-line tools or credentials: Dev Auto is instructions for the agent only.
Does Dev Auto 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 Dev Auto 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 Dev Auto use?
Dev Auto 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 Dev Auto use?
About 1.8k tokens (SKILL.md is roughly 7.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 893 tokens, read only when the agent opens those files.
What are the alternatives to Dev Auto?
Skills that share tags, products or a category with Dev Auto: Navigator (leewayworks/guochuang-gps, 106 stars), Breadcrumb Navigation (thedaviddias/Front-End-Checklist, 74k stars), Navigation Landmark (thedaviddias/Front-End-Checklist, 74k stars) and Keyboard Navigation (thedaviddias/Front-End-Checklist, 74k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Dev Auto?
hashgraph-online (a GitHub organization) maintains it in hashgraph-online/awesome-codex-plugins, which has 1,242 GitHub stars. The repository holds 686 skills in this directory. The repository was last updated on October 8, 2026.
Source: hashgraph-online/awesome-codex-plugins on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.