context-compression

context-compression is a skill for Claude Code from ihabkhaled/AI-Psychiatry. It costs 31 tokens per session (210 once invoked), scanned A, original, MIT.

A session-management skill that compresses long conversations and tool output into a short record of goals, decisions, evidence, blockers, and next steps.

In plain words
What is it for?
Use it when a session becomes large, repeated discussions need summarising, or another agent needs to take over the work.
Why use it?
Long sessions can make important context hard to find or lose it during a handoff. A compact record lets work continue without rereading everything.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the ai-psychiatry plugin — 55 skills shipped together

Good fit Use it when a session becomes large, repeated discussions need summarising, or another agent needs to take over the work.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ihabkhaled/ai-psychiatry/context-compression
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 ihabkhaled/AI-Psychiatry --skill context-compression
Clone the repo
git clone --depth 1 https://github.com/ihabkhaled/AI-Psychiatry

Made for: Claude Code.

Or install ai-psychiatry, the plugin that ships this one along with the rest of its 55 skills.

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 context-compression

README.md
[![agentmods](https://agentmods.dev/badge/skills/ihabkhaled/ai-psychiatry/context-compression.svg)](https://agentmods.dev/skills/ihabkhaled/ai-psychiatry/context-compression)
Your own site
<a href="https://agentmods.dev/skills/ihabkhaled/ai-psychiatry/context-compression"><img src="https://agentmods.dev/badge/skills/ihabkhaled/ai-psychiatry/context-compression.svg" alt="Measured on agentmods" height="20"></a>
Per session 31 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 210 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 $0.00031 $0.00210
Opus 5 $0.00015 $0.00105
Sonnet 5 $0.00006 $0.00042
Haiku 4.5 $0.00003 $0.00021

Measured 8d ago against content hash 5b4ba1b9a33e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

context-compression 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 8d 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.

.ai/skills/context-compression/SKILL.md · 37 lines

What it actually says

Context Compression

Core principle

Preserve actionable truth; drop raw reasoning, abandoned speculation, duplicate output, and outdated hypotheses.

Procedure

  1. Capture Goal, Completed, Remaining, Decisions, Evidence, Blocker, Deferred, and Next action.
  2. Keep exact errors, counts, paths, and commands only when material.
  3. Remove repeated explanations and obsolete hypotheses.
  4. Separate temporary state from durable knowledge.
  5. Validate important facts against current source.
  6. Write the compact state to the task context.

Required output

A short structured resume record with the eight required fields.

Limits

Use the smallest state that supports reliable continuation.

Common mistakes

Do not store chain-of-thought, giant logs, or promote temporary debugging to memory.

Stop condition

Stop when a future agent can resume without rereading the whole repository.

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. 8d ago First seen · 37 lines · 31 tokens per session scan A 5b4ba1b9a33e

Subscribe to this mod's changes

context-compression is a skill published in the GitHub repository ihabkhaled/AI-Psychiatry (3 stars, last pushed 23d ago), licensed MIT. It adds 31 tokens to every session and 210 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.

Related

Other skills, from other repositories

semantix

Install and use the semantix memory kernel as a middleware in your agent: extract user preferences / workflows / experience from past sessions, retrieve and inject them on demand. One binary + your agent's own tools.

Gnosil/semantix · 47 tokens

context-budget

Use when a long-horizon task is filling the context window and you must decide what to keep, offload, drop, or hand off to a fresh window — when to compact, what the summary must preserve, and whether to isolate a read-heavy subtask in a subagent. NOT dollar spend or caps (that is cost-tracking), NOT finding context…

ericrisco/rsc-harness · 82 tokens

continuous-learning

Use when a mistake, correction, or surprise taught the workspace something that must stick — a retro or postmortem, the same agent error corrected twice, a resolved bug's root cause, scattered notes-to-self — and route that lesson to the durable surface that fires next time. NOT a forward choice with alternatives…

ericrisco/rsc-harness · 73 tokens

self-improvement

Captures lessons and promotes recurring patterns.

andreaswasita/copilot-agents-dojo · 12 tokens

evolve

Use this skill when extracting session patterns into reusable learnings. Three modes: analyze (extract from session history), review (edit/manage existing learnings), list (display active learnings). Manages .orchestrator/metrics/learnings.jsonl.

Kanevry/session-orchestrator · 53 tokens

memory-cleanup

Use this skill when performing manual memory consolidation (Dream-equivalent). Reviews, consolidates, and prunes memory files under /.claude/projects//memory/. Run after major refactors, every 5+ sessions, or when memory quality degrades (broken links, stale references, contradictions, MEMORY.md > 200 lines). Invoke…

Kanevry/session-orchestrator · 77 tokens