session-start

session-start is a skill for Claude Code, Codex from Skyfox-io/Memex. It costs 45 tokens per session (1,836 once invoked), scanned A, original, MIT.

A session-opening routine for Memex, a workspace memory system that stores notes and indexes for later use. It checks the workspace and prepares a concise context briefing.

In plain words
What is it for?
Use it when starting or resuming work, after clearing the conversation, or when the current workspace context may be outdated.
Why use it?
It helps the coding agent recover relevant context quickly and notice when files changed after the previous session ended.

Skill for Claude CodeCodex

Part of the memex plugin — 17 skills shipped together

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/skyfox-io/memex/session-start
Any agent
npx skills add Skyfox-io/Memex --skill session-start
Clone the repo
git clone --depth 1 https://github.com/Skyfox-io/Memex

Made for: Claude Code, Codex.

Or install memex, the plugin that ships this one along with the rest of its 17 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-start

README.md
[![agentmods](https://agentmods.dev/badge/skills/skyfox-io/memex/session-start.svg)](https://agentmods.dev/skills/skyfox-io/memex/session-start)
Your own site
<a href="https://agentmods.dev/skills/skyfox-io/memex/session-start"><img src="https://agentmods.dev/badge/skills/skyfox-io/memex/session-start.svg" alt="Measured on agentmods" height="20"></a>
Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,836 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 $0.00045 $0.01836
Opus 5 $0.00023 $0.00918
Sonnet 5 $0.00009 $0.00367
Haiku 4.5 $0.00005 $0.00184

Measured 3d ago against content hash 416c6272ebe5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

session-start 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 3d 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.

memex/skills/session-start/SKILL.md · 134 lines

How it starts

The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Memex - Session Start

Wikilink rule: When referencing files in any markdown you write, use [[filename]] format. Plain-text filenames break Obsidian graph connectivity.

Orient fast, deliver a tight briefing.

Step 1: Detect workspace state

Run WORKSPACE_ROOT=$(pwd) && echo "$WORKSPACE_ROOT" via Bash.

Check _MANIFEST.md at the workspace root:

  • No manifest: tell the user to run /memex:init to set up structured memory here, then stop.
  • Marker present and current: full Memex mode, continue.
  • Anything else (no marker, or an outdated marker): read references/workspace-modes.md, then continue.

Unclean-close detection (mtime-based). No session lock exists. If any workspace .md file (excluding .git, .claude, .obsidian, memex, node_modules) is newer than status.md by 5+ minutes, the previous session likely skipped session-end — append after the briefing:

⚠ Files were modified after the last status.md update. The previous session may not have closed cleanly. Run /memex:update to refresh status, or describe what's been happening and we'll capture it.

Otherwise no warning — the only state check, no lock file involved.

Step 2: Scan the manifest

Read _MANIFEST.md's Tier 1/Tier 2 summaries and Hub Map (hub-to-domain mapping) without opening every file.

Resolve paths (first match wins): manifest config table → convention (memory/status.md, session-log.md, decisions.md, glossary.md, scratch/ideas.md or ideas.md) → search by name.

Step 3: Load context

Read in order: status.md (full file — priorities/blockers) → session-log.md (top entry only, stop at first ---) → decisions.md (last 5 entries) → ideas.md (skim, note routing) → memory/_CLOSETS.md if present (typed-field index over Tier 1 files — subjects/people/claims/decisions/dates/status — for field-level lookups instead of re-scanning full text).

Missing file: note briefly, continue. If memory/_CLOSETS.md is missing on a 2.1.x+ workspace, flag it for Step 6 (memory closets missing — run /memex:reindex --hub memory).

Read the full file on GitHub · 134 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 3d ago First seen · 134 lines · 45 tokens per session scan A 416c6272ebe5

Subscribe to this mod's changes

session-start is a skill published in the GitHub repository Skyfox-io/Memex (17 stars, last pushed 1mo ago), licensed MIT. It adds 45 tokens to every session and 1,836 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

obsidian

Comprehensive guidelines for Obsidian.md plugin development including ESLint rules from eslint-plugin-obsidianmd v0.4.1, TypeScript best practices, memory management, API usage (requestUrl vs fetch), UI/UX standards, popout window compatibility, community.obsidian.md submission process, and Scorecard optimization. Use…

gapmiss/obsidian-plugin-skill · 105 tokens

paid-ads

When the user wants help with paid advertising campaigns on Google Ads, Meta (Facebook/Instagram), LinkedIn, or other ad platforms. Also trigger on "PPC", "paid media", "ROAS", "CPA", "ad campaign", "retargeting", "audience targeting", "Google Ads setup", "Facebook Ads strategy", "LinkedIn Ads". Covers campaign…

Sudhakaran88/solopreneur-skills · 102 tokens

sales-enablement

When the user wants to create sales collateral, pitch decks, one-pagers, objection handling docs, or demo scripts. Also trigger on "sales deck", "pitch deck", "one-pager", "leave-behind", "objection handling", "ROI calculator", "demo script", "talk track", "sales playbook", "proposal template". For competitor battle…

Sudhakaran88/solopreneur-skills · 103 tokens

aia-generation

Run an AI impact assessment — structured intake, risk analysis, UK regulatory classification (UK GDPR / DPA 2018, ICO AI guidance, sector-specific UK regulation), EU AI Act analysis where EU nexus exists, policy consistency diff, and recommendation with conditions. Uses the house-style structure learned from the seed…

uk-agents/uk-legal-plugins · 149 tokens

cold-start-interview

Run the cold-start interview — learns your UK AI governance practice and writes /.claude/plugins/config/uk-legal-plugins/ai-governance-legal-uk/CLAUDE.md from your AI policy, a reference impact assessment, and key vendor AI agreements. Use when the practice profile is missing or contains [PLACEHOLDER] markers, or when…

uk-agents/uk-legal-plugins · 101 tokens

integration-management

Post-completion M&A integration tracker — phased workplan, consent tracking, contract assignment at scale, weekly status reports. Initialises from whatever deal artefacts are available (purchase agreement, deal summary, closing checklist) and connects to deal-context.md and closing-checklist.yaml from the M&A…

uk-agents/uk-legal-plugins · 103 tokens