session-memory-first-compaction

session-memory-first-compaction is a skill for Claude Code, Codex from ychampion/cskill-agents. It costs 23 tokens per session (377 once invoked), scanned A, original, MIT.

A context-management method that tries a lightweight saved session summary before summarising the entire conversation. The full summary is used only when the saved summary is unavailable.

In plain words
What is it for?
It is for coding agents that need to shorten long sessions while preserving session boundaries and cleanup state.
Why use it?
It reduces the work and context cost of automatic conversation compaction when a usable summary already exists.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit It is for coding agents that need to shorten long sessions while preserving session boundaries and cleanup state.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ychampion/cskill-agents/session-memory-first-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 ychampion/cskill-agents --skill session-memory-first-compaction
Clone the repo
git clone --depth 1 https://github.com/ychampion/cskill-agents

Made for: Claude Code, Codex.

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 session-memory-first-compaction

README.md
[![agentmods](https://agentmods.dev/badge/skills/ychampion/cskill-agents/session-memory-first-compaction/github.svg)](https://agentmods.dev/skills/ychampion/cskill-agents/session-memory-first-compaction)
Your own site
<a href="https://agentmods.dev/skills/ychampion/cskill-agents/session-memory-first-compaction"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/session-memory-first-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 session-memory-first-compaction

Your own site · 80×15
<a href="https://agentmods.dev/skills/ychampion/cskill-agents/session-memory-first-compaction"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/session-memory-first-compaction.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 23 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 377 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 $0.00023 $0.00377
Opus 5 $0.00012 $0.00188
Sonnet 5 $0.00005 $0.00075
Haiku 4.5 $0.00002 $0.00038

Measured 8d ago against content hash cdb3b9857aa7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

session-memory-first-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 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.

agents/claude-code/skills/session-memory-first-compaction/SKILL.md · 30 lines

What it actually says

SKILL: Session Memory First Compaction

Domain: context-management
Trigger: Apply when an auto-compact flow can query a session-memory summary before running the heavier legacy compaction path. Source Pattern: Distilled from reviewed lightweight summary-first and fallback compaction implementations.

Core Method

When auto-compaction fires, try the lightweight session-memory summary path first. If it returns a usable summary, treat that as a successful compaction and skip the heavier full-conversation compaction path. Only fall back to the heavyweight path when the lightweight summary is unavailable. This keeps cached or precomputed summaries in charge whenever possible and reserves the costly path for true misses.

Key Rules

  • Try the lightweight session-memory compaction path before the heavyweight full-conversation path every time auto-compaction triggers.
  • On success, reset last summarized IDs and run any post-compact cleanup to keep boundary metadata in sync.
  • Notify prompt-cache break detection so repeated compactions don’t misreport context flushes.
  • Return early with wasCompacted: true so callers skip the fallback path.
  • Only fall through to compactConversation when session memory compaction returns null.

Example Application

Auto-compaction finds a fresh session-memory summary, accepts it as the compaction result, records success, and avoids calling the heavyweight compaction path at all.

Anti-Patterns (What NOT to do)

  • Don’t always run the heavyweight compaction first; you waste CPU and risk prompt-too-long errors that session memory could avoid.
  • Don’t skip the cleanup steps that reset lastSummarizedMessageId and notify cache detectors when the lightweight path wins.
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 · 30 lines · 23 tokens per session scan A cdb3b9857aa7

Subscribe to this mod's changes

session-memory-first-compaction is a skill published in the GitHub repository ychampion/cskill-agents (36 stars, last pushed 5mo ago), licensed MIT. It adds 23 tokens to every session and 377 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 2026-09-03.