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.
npx skills add ychampion/cskill-agents --skill session-memory-first-compactiongit clone --depth 1 https://github.com/ychampion/cskill-agentsWrote 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.
[](https://agentmods.dev/skills/ychampion/cskill-agents/session-memory-first-compaction)<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.
<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>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 5.1 | $0.00023 | $0.00377 |
| Opus 5 | $0.00012 | $0.00188 |
| Sonnet 5 | $0.00005 | $0.00075 |
| Haiku 4.5 | $0.00002 | $0.00038 |
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.
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: trueso callers skip the fallback path. - Only fall through to
compactConversationwhen session memory compaction returnsnull.
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
lastSummarizedMessageIdand notify cache detectors when the lightweight path wins.
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.
- 8d ago First seen · 30 lines · 23 tokens per session scan A cdb3b9857aa7
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.
Other skills, from other repositories
grape
Use Grape MCP for Codex context continuity in coding repositories. Use when a task needs repeated-turn context, omitted context restore, stale-context checks, invalidation checks, or safe continuity across branch and dirty-worktree changes.
learn
Diagnose and fix agent behavioral surfaces when the user corrects a mistake — connects to Claude native memory.
ackit-context-optimization
Build budgeted context packs and trim instruction bloat for coding agents.
chain
Inject the 3 most recent session IDs for the current workspace into the prompt before Claude responds. Use when starting work and wanting recent session context.
context-efficient-coding
Use ContextFlux to minimize coding-agent context and tool calls when exploring, planning, debugging, reviewing, or modifying an unfamiliar or multi-file repository. Trigger for codebase discovery, symbol search, architecture questions, cross-file changes, error tracing, review feedback, test discovery, or any request…
k-knowledge
Instructions for recording stable project facts in AGENTS.md or a project map. AGENTS.md is a file that stores guidance for coding agents.