strategic-context-compaction

strategic-context-compaction is a skill for Claude Code from yeaight7/agent-powerups. It costs 59 tokens per session (944 once invoked), scanned A, original, Apache-2.0.

A method for deciding when to shorten an agent's working context at meaningful stage changes, such as moving from research to planning or implementation.

In plain words
What is it for?
It helps manage long sessions and phase changes while keeping task lists, files, and saved work aligned with the remaining conversation.
Why use it?
Compacting at the wrong time can lose paths, names, and reasoning; compacting at a sensible boundary removes dead ends while preserving useful state.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions CLAUDE.md; names the TodoWrite tool; mentions AGENTS.md.

Part of the dev-vitals plugin — 14 skills, 4 commands, 1 agent shipped together

Good fit It helps manage long sessions and phase changes while keeping task lists, files, and saved work aligned with the remaining conversation.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/yeaight7/agent-powerups/strategic-context-compaction
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.

Any agent
npx skills add yeaight7/agent-powerups --skill strategic-context-compaction
Clone the repo
git clone --depth 1 https://github.com/yeaight7/agent-powerups

Made for: Claude Code.

Or install dev-vitals, the plugin that ships this one along with the rest of its 14 skills, 4 commands, 1 agent.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for strategic-context-compaction

README.md
[![agentmods](https://agentmods.dev/badge/skills/yeaight7/agent-powerups/strategic-context-compaction/github.svg)](https://agentmods.dev/skills/yeaight7/agent-powerups/strategic-context-compaction)
Your own site
<a href="https://agentmods.dev/skills/yeaight7/agent-powerups/strategic-context-compaction"><img src="https://agentmods.dev/badge/skills/yeaight7/agent-powerups/strategic-context-compaction/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for strategic-context-compaction

Your own site · 80×15
<a href="https://agentmods.dev/skills/yeaight7/agent-powerups/strategic-context-compaction"><img src="https://agentmods.dev/badge/skills/yeaight7/agent-powerups/strategic-context-compaction.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 944 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00059 $0.00944
Opus 5 $0.00030 $0.00472
Sonnet 5 $0.00012 $0.00189
Haiku 4.5 $0.00006 $0.00094

Measured yesterday against content hash 3e3293f94859, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-15, from the pricing page.

Security

Grade A, and why

strategic-context-compaction 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.

plugins/dev-vitals/skills/strategic-context-compaction/SKILL.md · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Purpose

Compact at logical boundaries to preserve high-value context while clearing noise. Arbitrary or mid-task compaction loses critical state -- file paths, variable names, partial reasoning -- that is expensive to reconstruct.

When to Use

  • The context window is filling and you are at a phase boundary (research, planning, implementation, debugging)
  • A failed approach left dead-end reasoning that pollutes the next attempt
  • You are starting a conceptually distinct task in the same session
  • A prior mid-task compaction dropped state you then had to rebuild

Inputs

  • The current session state and which phase transition is approaching
  • Knowledge of what is already saved durably (task list, files, git, memory) versus only in conversation

Workflow

  1. Decide whether to compact by transition. Use the boundary table; default to NOT compacting mid-work.

    Transition Compact? Reason
    Research -- Planning Yes Research context is bulky; the plan is the distilled output
    Planning -- Implementation Yes Plan is saved in tasks/files; context is free to reset
    Implementation -- Testing Maybe Keep if tests reference recent code; compact if switching focus area
    Debugging -- Next feature Yes Debug traces pollute unrelated work
    Mid-implementation No Losing file paths, variable names, partial state is costly
    After a failed approach Yes Clear dead-end reasoning before trying a new approach
  2. Save anything you cannot reconstruct cheaply before compacting.

    • Write the plan to a task list or file before compacting after research
    • Commit or stash work-in-progress code before compacting after debugging
    • Note key file paths in the next prompt if they will be needed again
  3. Know what survives versus what is lost. Anything in the Lost column must be persisted in step 2 first.

    Survives Lost
    CLAUDE.md / AGENTS.md instructions Intermediate reasoning
    Task list (TodoWrite) File contents read in session
    Files on disk Tool call history
    Git state Verbally stated preferences
    Memory files Multi-step conversation context

Read the full file on GitHub · 80 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 · 80 lines · 59 tokens per session scan A 3e3293f94859

Subscribe to this mod's changes

strategic-context-compaction is a skill published in the GitHub repository yeaight7/agent-powerups (6 stars, last pushed 2d ago), licensed Apache-2.0. It adds 59 tokens to every session and 944 once invoked, about $0.0003 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 2026-09-14.