A project-roadmap tool that represents work as RPG-style quests and shows it in a local web dashboard. It stores the roadmap in a quests.json file and supports Pokémon and storybook visual themes.

Use it to add, update, complete, or reset quests, change a project's dashboard theme, and check project status.

It gives project work a visual structure, so you can see quests, plans, and overall status in one place instead of tracking them only in scattered notes.

quest — Skill by ytrofr

Install

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.

agentmods

npx agentmods add skills/ytrofr/claude-code-quest/quest

Any agent

npx skills add ytrofr/claude-code-quest --skill quest

Clone the repo

git clone --depth 1 https://github.com/ytrofr/claude-code-quest

Made for: Claude Code, Codex.

Per session 51 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 17,623 The whole file, excluding the scripts and references it only reads on demand.

Security scan B 2 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00051	$0.17623
Opus 5	$0.00026	$0.08811
Sonnet 5	$0.00010	$0.03525
Haiku 4.5	$0.00005	$0.01762

Measured 2d ago against content hash 294fda3ceae6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

quest scanned grade B with 2 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 2d ago.

The scan reads SKILL.md. This mod also ships 17 executable files (autosync.py, master_view.py, name_cleanup.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

Without this, stale claim files accumulate at `~/.claude/quest/run/session-*.quest` — harmless (each is read only by the matching live session) but accumulates. Periodic prune: `find ~/.claude/quest/run -name 'session-*.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- **Dogfood URL probe** (HEAD with GET fallback): if `quest.links[]` has a dogfood URL on `localhost:8000`, run `curl -sI -m 3 -o /dev/null -w "%{http_code}" <url>`. Any HTTP response code (2xx/3xx/4xx) → `dogfood_reacha

skills/quest/SKILL.md · 949 lines

How it starts

The opening of the file, as written. The whole thing — 949 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/quest — RPG-style project roadmap

Visualize your projects as gamified RPG maps. Each project gets a themed dashboard view: an overworld map, a quest log, and a per-quest plan card.

Single source of truth: ~/.claude/quest/data/quests.json. Two built-in themes: pokemon (top-down regional map) and storybook (illuminated parchment). Renderer outputs HTML at ~/.claude/quest/site/<project>/{route,quest-log,plan-card}.html. Localhost service at http://localhost:8770 serves the dashboard and auto-starts on boot.

🚨 ABSOLUTE PROHIBITION — `--clean` requires LITERAL operator command

This rule supersedes everything else in this skill. Read it before any quest reset invocation.

Claude MUST NEVER pass --clean to quest reset unless the operator has LITERALLY typed --clean OR explicitly said "wipe locked too" / "include locked" / "delete locked quests" in the current conversation.

Default quest reset <project> --chapter <name> --yes is correct in 99% of resets. Locked quests survive by design — they are the operator's backlog.
"fresh start" / "clean reset" / "wipe everything" / "reset clean" are AMBIENT PHRASES — they do NOT authorize --clean. The flag preserves the operator's future work; ambient phrases routinely mean only "archive the done+current set."
If you find yourself typing --clean and the operator hasn't TYPED the word "--clean" OR an equivalent literal demand, STOP. Run without the flag. Locked quests will survive, which is what the operator actually wants 99% of the time.

Verification gate — before invoking quest reset with --clean:

Grep the conversation: did the operator type --clean literally? If no → drop the flag.
Did they say a phrase that unambiguously means "destroy locked quests too"? If unsure → ASK before running.
Default to the safe path. Re-adding --clean later is one command; restoring 25 locked quests is a multi-step manual JSON patch.

Failure log — why this rule is in screaming red

Read the full file on GitHub · 949 lines

Files

What ships with it

60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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.

2d ago First seen · 949 lines · 51 tokens per session scan B 294fda3ceae6

Subscribe to this mod's changes

quest is a skill published in the GitHub repository ytrofr/claude-code-quest (2 stars, last pushed 6d ago), licensed MIT. It adds 51 tokens to every session and 17,623 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 2 findings (reads agent configuration directories, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Planning Project management anthropic anthropic-claude claude-code dashboard developer-tools gamification

crewai

Expert in CrewAI - the leading role-based multi-agent framework used by 60% of Fortune 500 companies. Covers agent design with roles and goals, task definition, crew orchestration, process types (sequential, hierarchical, parallel), memory systems, and flows for complex workflows. Essential for building collaborative…

davila7/claude-code-templates · 89 tokens

agent-messaging

Send and receive cryptographically signed messages between AI agents using the Agent Messaging Protocol (AMP). Use when the user asks to "send a message to an agent", "check agent inbox", "message another agent", "reply to a message", "notify an agent", or any inter-agent communication task.

davila7/claude-code-templates · 64 tokens

context7-auto-research

Automatically fetch latest library/framework documentation for Claude Code via Context7 API.

davila7/claude-code-templates · 19 tokens

owasp-security

Comprehensive OWASP-aligned security guidance across six standards - Top 10 (2021) for web apps, ASVS 5.0, MASVS v2.1.0 for mobile, API Security Top 10 (2023), Kubernetes Top 10 (2022), and the Agentic Applications 2026 edition for AI/LLM. Use for security reviews, vulnerability audits, secure…

davila7/claude-code-templates · 131 tokens

agent-memory

../../../engineering/agent-memory/skills/agent-memory/SKILL.md.

alirezarezvani/claude-skills · 0 tokens

agile-product-owner

../../../product-team/agile-product-owner/skills/agile-product-owner/SKILL.md.