A context-shortening workflow that creates a tailored /compact instruction while preserving important decisions and removing debugging noise. Context is the information available to the coding agent in a session.

Use it to inspect recent files and session artifacts, infer what happened, and prepare a concise handoff before compacting context.

It helps continue a long session without losing key work, decisions, or project state.

compact — Skill by billbuchanan-code

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/billbuchanan-code/claude-code-power-setup/compact

Any agent

npx skills add billbuchanan-code/claude-code-power-setup --skill compact

Clone the repo

git clone --depth 1 https://github.com/billbuchanan-code/claude-code-power-setup

Made for: Claude Code, Codex.

Per session 13 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 854 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.

Model	Per session	Once invoked
Fable 5	$0.00013	$0.00854
Opus 5	$0.00006	$0.00427
Sonnet 5	$0.00003	$0.00171
Haiku 4.5	$0.00001	$0.00085

Measured yesterday against content hash 4bce84ec3a7b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

compact 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/compact/SKILL.md · 104 lines

How it starts

The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Smart Compact Instruction Generator

Analyze the current session to generate a tailored /compact instruction that preserves important context and discards noise.

Process

Step 1: Infer Session Contents

You do not have direct access to the conversation history. Instead, infer what happened in the session from available signals:

Check git state: Use Glob and Grep to look at:
- Files recently modified (check modification times via ls -lt patterns or git status)
- Any HANDOFF.md or TODO files that describe session work
- .claude/ directory for any session artifacts
Detect agent delegation patterns: Look for signs that sub-agents were used:
- Multiple files explored in a short time (breadth-first patterns)
- Search result files or temporary analysis files
- Changes across many unrelated directories (suggests parallel agent work)
Detect MCP server usage: Check for:
- .mcp.json or mcp_config.json files in the project
- References to external services in recently changed files
- Configuration files for Slack, GitHub, databases, etc.
Identify key decisions: Look for:
- New dependencies added (package.json, Cargo.toml, requirements.txt, go.mod changes)
- New files created (architectural decisions about structure)
- Configuration file changes (tooling/infrastructure decisions)
- Pattern choices visible in code (e.g., choosing a specific design pattern)
Identify debugging noise: Look for signs of troubleshooting:
- Files with many recent modifications (iterative debugging)
- Test files that were changed multiple times
- Log or output files
- Temporary files or scratch work

Step 2: Categorize Context

Sort everything into two categories:

Preserve (high-value context that is expensive to reconstruct):

Architecture and design decisions made
File paths that were created or significantly modified
Agent delegation results (what was found, what was decided)
MCP connection states and which servers are active
User preferences or constraints stated during the session
Working solutions that were arrived at
Branch name and what it represents
Key relationships between files discovered during exploration

Read the full file on GitHub · 104 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.

yesterday First seen · 104 lines · 13 tokens per session scan A 4bce84ec3a7b

Subscribe to this mod's changes

compact is a skill published in the GitHub repository billbuchanan-code/claude-code-power-setup (2 stars, last pushed 1mo ago), licensed MIT. It adds 13 tokens to every session and 854 once invoked, about $0.0001 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.

Debugging Productivity

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