session-consolidation

session-consolidation is a skill for Claude Code from terrizoaguimor/celiums-memory. It costs 47 tokens per session (637 once invoked), scanned A, original, Apache-2.0.

A session handoff routine that records what was finished, what remains open, and what should happen next.

In plain words
What is it for?
It is for saving a concise record after major work, before context is lost, or when the user asks to continue later.
Why use it?
It reduces the chance of losing useful project context when a work session ends or the conversation is restarted.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions Claude Code.

Part of the celiums plugin — 9 skills shipped together

Good fit It is for saving a concise record after major work, before context is lost, or when the user asks to continue later.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/terrizoaguimor/celiums-memory/session-consolidation
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 terrizoaguimor/celiums-memory --skill session-consolidation
Clone the repo
git clone --depth 1 https://github.com/terrizoaguimor/celiums-memory

Made for: Claude Code.

Or install celiums, the plugin that ships this one along with the rest of its 9 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 session-consolidation

README.md
[![agentmods](https://agentmods.dev/badge/skills/terrizoaguimor/celiums-memory/session-consolidation/github.svg)](https://agentmods.dev/skills/terrizoaguimor/celiums-memory/session-consolidation)
Your own site
<a href="https://agentmods.dev/skills/terrizoaguimor/celiums-memory/session-consolidation"><img src="https://agentmods.dev/badge/skills/terrizoaguimor/celiums-memory/session-consolidation/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-consolidation

Your own site · 80×15
<a href="https://agentmods.dev/skills/terrizoaguimor/celiums-memory/session-consolidation"><img src="https://agentmods.dev/badge/skills/terrizoaguimor/celiums-memory/session-consolidation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 637 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00047 $0.00637
Opus 5 $0.00023 $0.00318
Sonnet 5 $0.00009 $0.00127
Haiku 4.5 $0.00005 $0.00064

Measured 11d ago against content hash d04bb2b29a8c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

session-consolidation 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 11d 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.

packages/plugin-claude-code/skills/session-consolidation/SKILL.md · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cognitive Reflex: Session Consolidation

Neural Basis

Sleep transforms labile short-term memories into stable long-term ones via replay in the hippocampus-cortex loop. This is why "sleeping on it" works — consolidation reorganizes, strengthens important memories, and discards noise.

Without consolidation, every session is a fresh start with scattered fragments.

Diekelmann, S. & Born, J. (2010). The memory function of sleep. Nature Reviews Neuroscience, 11(2), 114-126.

When It Fires

End-of-session signals:

  • User: "ok thanks", "bye", "that's it", "I'm done", "later"
  • Session duration exceeds 30 minutes of substantive work
  • A major milestone completes (deploy, PR merged, feature finished)
  • Context window approaching compaction
  • User explicitly asks to "save where we are"

The Instinct

One structured memory. Three fields. Always.

remember(
  content: "SESSION HANDOFF <YYYY-MM-DD> — \
            DONE: <what was completed> — \
            OPEN: <what is unresolved> — \
            NEXT: <what should happen in the next session>",
  tags: ["session-handoff", "<project>"]
)

The three fields are non-negotiable:

  1. DONE — concrete outcomes, not effort ("deployed v0.2.0" not "worked on deploy")
  2. OPEN — unresolved blockers, decisions pending, half-done work
  3. NEXT — the first concrete action for tomorrow-you

Failure Mode

Without consolidation, the next session opens cold. The user has to re-explain context, re-establish where things are, re-decide what's next. Every session costs 10 minutes of re-orientation that consolidation would have eliminated.

Worse: unresolved blockers get forgotten. A bug that "we'll look at next time" vanishes into the void.

Why Three Fields

DONE anchors accomplishment. OPEN prevents dropped context. NEXT enables cold-start resumption.

Skip any of the three and the handoff breaks:

  • No DONE → you don't know what state things are in
  • No OPEN → blockers re-surface as surprises
  • No NEXT → momentum dies

Read the full file on GitHub · 72 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. 11d ago First seen · 72 lines · 47 tokens per session scan A d04bb2b29a8c

Subscribe to this mod's changes

session-consolidation is a skill published in the GitHub repository terrizoaguimor/celiums-memory (23 stars, last pushed 18d ago), licensed Apache-2.0. It adds 47 tokens to every session and 637 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 2026-08-30.

Related

Other skills, from other repositories

openmemory

Manage persistent memory via OpenMemory MCP. TRIGGER when: user says "remember this", "save to memory", "store this", "recall", "what do you remember about", "check memory", "forget this", "delete memory", "clean up memory", or when agent forms a stable conclusion worth persisting. DO NOT TRIGGER when: user refers to…

CaviraOSS/OpenMemory · 96 tokens

ccs-align

Run the CCS Align seat's hourly breathing cycle — prove the local claude-mem worker is healthy, pull needle observations through search → timeline → getobservations, land them in a seat-owned middle cache via atomic grab → append → filter exclude-marks → replace, manage exclude marks, and walk house → project → seat…

thedotmack/claude-mem · 136 tokens

design-is

Audit a design against Dieter Rams' ten "Good design is..." principles, then hand off a /make-plan prompt for one of three outcomes — new design, refine design, or redesign. Use when the user says "audit this design", "design review", "check this UI against Rams", "is this UI good", "critique this design", "design…

thedotmack/claude-mem · 91 tokens

weekly-digests

Generate a serial week-by-week narrative digest of a project's full claude-mem timeline. Splits the timeline into per-ISO-week files, then runs one consecutive subagent per week — each receiving the prior week's carry-forward block — to produce one chapter per ISO week of data. Use when asked for "weekly digests"…

thedotmack/claude-mem · 93 tokens

smart-explore

Token-optimized structural code search using tree-sitter AST parsing. Use instead of reading full files when you need to understand code structure, find functions, or explore a codebase efficiently.

thedotmack/claude-mem · 41 tokens

wowerpoint

Turn one document into a kawaii NotebookLM slide-deck PDF. Use for "wowerpoint this", "make a deck about ", "turn this report into slides", or any request to render a single document as shareable narrative slides.

thedotmack/claude-mem · 55 tokens