side-quest

A background-task workflow that sends side quests to separate agents while the main conversation remains available. It chooses a model based on the task's difficulty and uses an XP ledger and setup scripts to track the system.

In plain words
What is it for?
Launching delegated tasks with /side-quest, setting up the required scripts and hooks, and tracking side-quest progress and experience.
Why use it?
It lets longer or separate tasks run without taking over the main interaction, provided the side-quest setup has been completed.

Skill for Claude CodeCodex

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

Made for: Claude Code, Codex.

Per session 161 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,406 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00161 $0.02406
Opus 5 $0.00081 $0.01203
Sonnet 5 $0.00032 $0.00481
Haiku 4.5 $0.00016 $0.00241

Measured yesterday against content hash 9a81be87a7dc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

side-quest scanned grade B with 1 finding 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 yesterday.

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.

Run `/side-quest:setup` once after installing the plugin (or after updating it) — it delegates to the `side-quest-setup` agent, the single source of truth for what gets installed, and is idempotent — safe to re-run after
plugins/side-quest/skills/side-quest/SKILL.md · 121 lines

How it starts

The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.

First-time setup

Run /side-quest:setup once after installing the plugin (or after updating it) — it delegates to the side-quest-setup agent, the single source of truth for what gets installed, and is idempotent — safe to re-run after every plugin update. It deploys xp.sh, xp_core.py, xp-sync-daemon.sh, and statusline-command.sh to their stable paths; installs the cross-machine MQTT sync daemon; merges the statusLine block, the Stop hook, and the PostToolUse tick hook into ~/.claude/settings.json; and asks for approval before adding the ambient XP rule to ~/.claude/CLAUDE.md. See agents/side-quest-setup.md for exactly what each hook does and why.

The ledger at ~/.claude/side-quest/xp.json is shared between the stable copy and the plugin script.

Side Quest

Preflight check

Before doing anything else, check if setup has been run:

test -f "$HOME/.claude/side-quest/xp.sh"

If the file is missing, stop and tell the user:

"⚔️ The side-quest ledger isn't set up on this machine yet. Run /side-quest:setup first — it deploys the XP scripts, configures the statusline, and walks you through the rest. (~2 minutes)"

Do not proceed with the quest until setup is confirmed.

If the file exists, continue normally.


Fire-and-forget task delegation with table-top flair. /side-quest <task> sends the work to background subagents and narrates the journey in D&D style — every themed response paired with a mandatory plain-English translation, so the flavor never costs you information.

How it works

  1. Parse the quest. The command argument is the task. No argument → a one-line tavern-keeper prompt asks what quest you seek. Anything that needs user input (ambiguous targets, choices, credentials) gets resolved before launch — background agents can't ask questions mid-quest. Destructive or outward-facing quests (push, deploy, delete, send) are confirmed first.

  2. Rate the Challenge Rating → pick the model.

    CR Difficulty Examples Model
    1–2 Trivial lookups, renames, single-file tweaks 🧝 haiku
    3–4 Standard refactors, multi-file features, research 🧙 sonnet
    5+ Boss fight complex, cross-cutting, architectural 🐲 opus

Read the full file on GitHub · 121 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. yesterday First seen · 121 lines · 161 tokens per session scan B 9a81be87a7dc

Subscribe to this mod's changes

side-quest is a skill published in the GitHub repository trtmn/agent-plugins (2 stars, last pushed 5d ago), licensed Unlicense. It adds 161 tokens to every session and 2,406 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens