quick

A lightweight workflow for short, one-off coding tasks that need little project context.

In plain words
What is it for?
It checks the project structure, reads only a short project-status summary when available, and starts the task without requiring a full session setup.
Why use it?
It reduces setup work for quick fixes, simple questions, and small research tasks.

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/gh33k/session-plugin/quick
Any agent
npx skills add gh33k/session-plugin --skill quick
Clone the repo
git clone --depth 1 https://github.com/gh33k/session-plugin

Made for: Claude Code, Codex.

Per session 9 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 986 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 $0.00009 $0.00986
Opus 5 $0.00005 $0.00493
Sonnet 5 $0.00002 $0.00197
Haiku 4.5 $0.00001 $0.00099

Measured yesterday against content hash 9edb2c755ea8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

quick 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 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.

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.

skills/quick/SKILL.md · 194 lines

How it starts

The opening of the file, as written. The whole thing — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.

session:quick

Start a lightweight session for quick, ad-hoc tasks. Minimal context loading, no session file ceremony, quick summary on completion.

When to Use

  • Small one-off tasks that don't warrant a full session
  • Quick fixes or tweaks
  • Simple questions about the codebase
  • Fast research or lookups
  • Tasks expected to take < 15 minutes

Instructions

When the user runs /session:quick [task], perform these steps:

1. Verify Project Structure

Check if session workflow has been initialized:

ls -d .project 2>/dev/null

If .project/ does not exist:

  • Proceed anyway - quick sessions don't require full setup
  • Just note: "No .project/ found, proceeding with minimal context"

2. Load Minimal Context

Extract only orientation from .project/state.md:

./scripts/extract-state.sh summary 2>/dev/null

This provides current focus and blocker count in one line.

Do not load full files unless specifically needed for the task.

3. Acknowledge Task

If a task was provided as an argument:

Quick session: {task}

Current focus: {from state.md Active Focus, or "unknown"}

Starting...

If no task was provided, ask:

Quick session mode. What do you need?

4. Execute Task

Work on the task directly:

  • Keep it focused and efficient
  • Don't create session files
  • Don't do extensive context loading
  • Ask clarifying questions only if essential

5. Quick Summary on Completion

When the task is complete, provide a brief summary:

Done!

What was done:
- {brief bullet points}

Files changed:
- {list any modified files, or "none"}

6. Optional State Update

If the quick task resulted in a significant change or decision:

Ask: "Should I note this in .project/state.md?"

If yes, add a brief entry to the "Recent Decisions" section:

- [Brief decision]: [One-line rationale] (quick session)

Do not update Active Focus or other sections for quick tasks.

What Quick Sessions Skip

  • No session file creation in .context/sessions/
  • No formal goal setting
  • No extensive context loading
  • No task status updates in beads (unless explicitly requested)
  • No formal session end process

Read the full file on GitHub · 194 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 · 194 lines · 9 tokens per session scan A 9edb2c755ea8

Subscribe to this mod's changes

quick is a skill published in the GitHub repository gh33k/session-plugin (2 stars, last pushed 7mo ago), licensed MIT. It adds 9 tokens to every session and 986 once invoked, about $0.0000 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.