load-session

load-session is a skill for Claude Code from faizkhairi/claude-code-blueprint. It costs 41 tokens per session (429 once invoked), scanned A, original, MIT.

A session-start routine that restores saved project context from files such as previous-session notes, preferences, reminders, decisions, and active project records. It is inactive when the project’s memory system is disabled or unavailable.

In plain words
What is it for?
Use it when starting a new conversation or continuing earlier work on a project that stores its context in a memory directory.
Why use it?
It reduces the need to repeat what happened in an earlier conversation. It brings back the relevant work state and highlights open reminders when memory is enabled.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: reads .claude/ paths; mentions CLAUDE.md.

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.

agentmods
npx agentmods add skills/faizkhairi/claude-code-blueprint/load-session
Any agent
npx skills add faizkhairi/claude-code-blueprint --skill load-session
Clone the repo
git clone --depth 1 https://github.com/faizkhairi/claude-code-blueprint

Made for: Claude Code.

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 load-session

README.md
[![agentmods](https://agentmods.dev/badge/skills/faizkhairi/claude-code-blueprint/load-session.svg)](https://agentmods.dev/skills/faizkhairi/claude-code-blueprint/load-session)
Your own site
<a href="https://agentmods.dev/skills/faizkhairi/claude-code-blueprint/load-session"><img src="https://agentmods.dev/badge/skills/faizkhairi/claude-code-blueprint/load-session.svg" alt="Measured on agentmods" height="20"></a>
Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 429 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00041 $0.00429
Opus 5 $0.00020 $0.00215
Sonnet 5 $0.00008 $0.00086
Haiku 4.5 $0.00004 $0.00043

Measured 6d ago against content hash 05335b529c92, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

load-session 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 6d 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.

skills/load-session/SKILL.md · 32 lines

What it actually says

Prerequisite check (run first): if ./memory/ does not exist OR ~/.claude/.memory-disabled marker file is present, this skill is a no-op. Output: "Memory persistence is disabled. Run ./setup.sh and choose to enable memory if you want this skill to work."

Restore context from the memory system:

  1. Read ./memory/core/session.md for where we left off

  2. Read ./memory/core/preferences.md for user preferences

  3. Read {MEMORY_MD_PATH} for technical context and project conventions

  4. Read ./memory/core/reminders.md for active reminders

  5. Read ./memory/core/decisions.md for architectural decision context

  6. Check ./memory/diary/current/ for the most recent diary entry (if any)

  7. Check ./memory/projects/active/ for active project files (scan directory)

  8. Read relevant topic files based on project context:

    • Check CLAUDE.md for topic file references relevant to the current project
    • Only load topic files related to the current working directory
  9. Summarize in a concise format:

    • Reminders: Display open reminders prominently at the top with any deadlines highlighted
    • Last session: What we were working on and where we left off
    • Pending: What's still in progress or needs attention
    • Active projects: Current project(s) and their session context
    • Priorities: Current goals and focus areas
    • Blockers: Any open questions or issues from last session
    • Preferences: Key communication and work style preferences

Keep the summary brief and actionable, focusing on what's needed to continue working effectively.

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. 6d ago First seen · 32 lines · 41 tokens per session scan A 05335b529c92

Subscribe to this mod's changes

load-session is a skill published in the GitHub repository faizkhairi/claude-code-blueprint (70 stars, last pushed 24d ago), licensed MIT. It adds 41 tokens to every session and 429 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.