quest

A workflow manager for non-trivial coding tasks that coordinates research, planning, implementation, context summaries, and review. It divides work into phases and uses supporting routines for each phase.

In plain words
What is it for?
Use it for complex or multi-file work, including research, planning, test-driven development (writing tests as part of the implementation process), implementation, and adversarial review of failure cases.
Why use it?
It provides checkpoints for understanding the code, planning changes, implementing them with tests, and looking for edge cases. This reduces the risk of making broad changes without verification.

Skill for Claude CodeCodex

Part of the fellowship plugin — 20 skills, 19 commands, 6 agents, 3 hooks shipped together

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/justinjdev/fellowship/quest
Any agent
npx skills add justinjdev/fellowship --skill quest
Clone the repo
git clone --depth 1 https://github.com/justinjdev/fellowship

Made for: Claude Code, Codex.

Or install fellowship, the plugin that ships this one along with the rest of its 20 skills, 19 commands, 6 agents, 3 hooks.

Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,663 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 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.

ModelPer sessionOnce invoked
Fable 5 $0.00047 $0.05663
Opus 5 $0.00023 $0.02831
Sonnet 5 $0.00009 $0.01133
Haiku 4.5 $0.00005 $0.00566

Measured 2d ago against content hash adfe1211c505, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

quest 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 2d 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.

plugin/skills/quest/SKILL.md · 378 lines

How it starts

The opening of the file, as written. The whole thing — 378 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Quest — Research, Plan, Implement

Overview

Orchestrates the full Research → Plan → Implement cycle with intentional compaction between phases. This is the hub skill that enforces context engineering discipline by invoking satellite skills at the right moments and maintaining hard gates between phases.

When to Use

  • Any task that involves more than a quick fix
  • When you want structured, disciplined progress through a complex change
  • When context management matters (large codebase, multi-file changes)

Phase Flow

Phase 0: Onboard ──→ EnterWorktree → /council
     │
     ▼
Phase 1: Research ──→ Explore agents / /gather-lore
     │                Goal: understand the system, identify files
     ▼
  /lembas
     │
     ▼
Phase 2: Plan ──────→ Plan mode / writing-plans
     │                Goal: explicit steps with file:line refs
     ▼
  /lembas
     │
     ▼
Phase 3: Implement ──→ TDD (test-driven-development) + execute plan
     │                 Goal: small verifiable changes via red-green-refactor
     ▼
  /lembas
     │
     ▼
Phase 3.5: Adversarial → balrog agent (edge cases, error paths, adversarial inputs)
     │                   Goal: find failure modes before review
     ▼
  /lembas
     │
     ▼
Phase 4: Review ─────→ /warden → /pr-review-toolkit:review-pr
     │                 → verification-before-completion
     │                 Goal: conventions + code quality + verified passing
     ▼
  /lembas
     │
     ▼
Phase 5: Complete ───→ finishing-a-development-branch
                       Goal: squash/merge, PR creation, cleanup

Process

External skill dependencies: Several steps invoke skills from the superpowers and pr-review-toolkit plugins (TDD, verification, branch finishing, PR review). If an invocation fails because the plugin is not installed, do not silently skip the step — perform the step's goal manually (write the failing test first yourself, run the verification commands yourself, review the diff yourself) and note the substitution in your phase output or gate message.

Read the full file on GitHub · 378 lines

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.

  1. 2d ago First seen · 378 lines · 47 tokens per session scan A adfe1211c505

Subscribe to this mod's changes

quest is a skill published in the GitHub repository justinjdev/fellowship (5 stars, last pushed 19d ago), licensed Apache-2.0. It adds 47 tokens to every session and 5,663 once invoked, about $0.0002 per session on Opus 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 2026-08-31.