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 agentmods add skills/skyfox-io/memex/session-endnpx skills add Skyfox-io/Memex --skill session-endgit clone --depth 1 https://github.com/Skyfox-io/MemexWrote 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/skyfox-io/memex/session-end)<a href="https://agentmods.dev/skills/skyfox-io/memex/session-end"><img src="https://agentmods.dev/badge/skills/skyfox-io/memex/session-end.svg" alt="Measured on agentmods" 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 | $0.00056 | $0.02636 |
| Opus 5 | $0.00028 | $0.01318 |
| Sonnet 5 | $0.00011 | $0.00527 |
| Haiku 4.5 | $0.00006 | $0.00264 |
Grade A, and why
session-end scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Memex - Session End
Wikilink rule: When referencing files in any markdown you write, use [[filename]] format. Plain-text filenames break Obsidian graph connectivity.
Leave the workspace clean for the next session. Work each step in order — no skipping, no asking permission between steps; execute everything, report at the end.
Session-end's work is proportional to the session (touched files, modified hubs, new decisions). Workspace-wide maintenance — graph rebuild, dedup, contradiction sweep, decisions compression — lives in /memex:reindex//memex:consolidate on their own cadence.
Step 1: Detect workspace and resolve paths
Run WORKSPACE_ROOT=$(pwd) && echo "$WORKSPACE_ROOT" via Bash.
No _MANIFEST.md: skip silently, stop. Otherwise resolve paths (first match wins): manifest config table → convention (memory/status.md, session-log.md, decisions.md, scratch/ideas.md or ideas.md) → search by name. No session lock — unconditional and idempotent.
Step 2: Synthesize the session
Before touching files, write a brief internal summary: files created/modified/moved, domains touched, decisions made, done vs. left open.
Step 3: Update status.md (idempotent)
- Update "Last updated" to today
- Remove completed items from "What's In Progress"
- Update "What's Blocked" — resolve/add blockers
- Update "Next Priorities" to reflect what's next
Idempotency check: strip the "Last updated" line from old and new content, hash both. Matching hashes (unchanged substance): skip the write entirely, including the date — prevents "ran twice" from compounding drift via timestamp churn.
Step 4: Write the session-log entry
Prepend to session-log.md (after the header, before existing entries):
## YYYY-MM-DD - [one-line title]
- [what changed - name files specifically]
- [decisions made or insights locked]
- [what's next / what was left open]
---
3-5 bullets. Past tense. Specific.
If the log now has more than 10 entries, archive the oldest — see references/log-rotation.md.
What ships with it
5 files 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.
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.
- 4d ago First seen · 198 lines · 56 tokens per session scan A 6482a8149af8
session-end is a skill published in the GitHub repository Skyfox-io/Memex (17 stars, last pushed 2mo ago), licensed MIT. It adds 56 tokens to every session and 2,636 once invoked, about $0.0003 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.
Other skills, from other repositories
wage-hour-qa
Jurisdiction-aware pay and working time Q&A — NMW/NLW compliance, overtime, rest breaks, holiday pay calculation, final pay, and employment status for pay purposes — answered for the specific jurisdiction with the controlling rule researched and cited rather than stated from memory. Use when the user asks any pay or…
obsidian-companion
Use when interacting with the user's Obsidian vault — reading, writing, searching, or chatting with notes using local RAG. Guides tool selection and writing strategy for all vault operations.
wiki-ingest
Use when the user wants to ingest external sources into the vault — PDFs, markdown files, transcripts, Readwise exports, or any document. Triggers on "ingest", "process document", "import into vault", "distill this", "add to vault", or "extract knowledge from".
vault-lint
Use when the user wants a health audit of the vault — stale content, provenance drift, frontmatter compliance, or MOC coverage gaps. Triggers on "lint vault", "vault health", "check vault", "stale notes", "vault audit", "vault quality", or "check conventions".
compound
Use when the user wants to promote cross-project knowledge to the global Engineering/ folder, or says "promote knowledge", "compound notes", "knowledge synthesis", or "find repeated ideas across projects".
links
Use when the user wants to explore connections between notes, see what links to or from a note, or says "links", "backlinks", "connections", or "graph".