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/sandsower/memento-vault/continue-worknpx skills add sandsower/memento-vault --skill continue-workgit clone --depth 1 https://github.com/sandsower/memento-vaultWrote 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/sandsower/memento-vault/continue-work)<a href="https://agentmods.dev/skills/sandsower/memento-vault/continue-work"><img src="https://agentmods.dev/badge/skills/sandsower/memento-vault/continue-work.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 5.1 | $0.00041 | $0.00541 |
| Opus 5 | $0.00020 | $0.00270 |
| Sonnet 5 | $0.00008 | $0.00108 |
| Haiku 4.5 | $0.00004 | $0.00054 |
Grade A, and why
continue-work 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 5d 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Continue Work
Fast context recovery. Gather local state first, vault search only when needed.
When to use
- User asks to continue, resume, or pick up where they left off
- User asks what was being worked on
- Starting a fresh session when memory has unfinished items
Process
Step 1 — Local context (do all in parallel)
Gather these simultaneously — no agents needed:
- Scope detection: Run
git rev-parse --show-toplevelto get the current worktree/repo path. Extract the scope name (last path component). If not in a git repo, use the current directory name. This is your scope key for filtering MEMORY.md. - MEMORY.md: Read the project's
MEMORY.mdfrom the auto memory path. Filter pending work to entries matching the current worktree only (look for## Pending - <worktree>/sections). Ignore pending entries from other worktrees. - Git state:
git branch --show-current,git log --oneline -10,git status --short. This tells you what branch, what was done recently, and what's uncommitted. - Active plan: Check the plans directory for the most recently modified plan file. If one exists and references the current branch or ticket, read it.
Step 2 — Present what you found
Give a brief summary:
- Worktree: current worktree path
- Branch: current branch name
- Recent work: 1-2 sentence summary from git log + any uncommitted changes
- Pending items: from MEMORY.md for this worktree only (if any)
- Active plan: link to plan file + current step (if any)
- Suggested next step: based on the above
Step 3 — Ask, don't act
Ask the user what they want to pick up. Do NOT start working autonomously.
Step 4 — Vault search (only if needed)
Skip the vault entirely unless:
- Local context is thin (no recent commits, no pending items, no plan)
- The user explicitly asks about history beyond the current branch
If vault search IS needed, spawn the concierge agent with a specific question — not a broad "find everything" query.
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.
- 5d ago First seen · 53 lines · 41 tokens per session scan A e83f75a495e2
continue-work is a skill published in the GitHub repository sandsower/memento-vault (12 stars, last pushed 22d ago), licensed MIT. It adds 41 tokens to every session and 541 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.
Other skills, from other repositories
garden-tending
Tend the knowledge garden — diagnose vault health, condense project memos into project.md overviews, create/merge cross-project topics, fix broken links, archive superseded notes, extend trails. Trigger on "tend the garden", "condense", "update project overview", "check vault health", "where are we with X?", "what…
curator-practice
Operating philosophy for autonomous memex curator tending — orientation protocol, signal triage, bounded work units, initiative thresholds, logging conventions. Trigger on cron-launched runs with no user prompt, "use your judgment", "tend without instructions", "do a pass on the vault", "I'll be away — do what needs…
memo-writing
How to write effective session memos — format, frontmatter schema, observation extraction, topic-signal append. Trigger on /memex:save, "save this for later", "remember this", "save what we discussed", "document this session", "create a memo", or when the [memex] activity nudge appears in context. Do NOT trigger for…
recall
Retrieve session memory across 4 modes — TEMPORAL (date browsing), KEYWORD (FTS lookup), DEEP (cross-session synthesis), LOAD (specific file). Trigger on "what did I do yesterday/last week", "why did we...", "remind me...", "find the memo about...", "last time we...", "patterns across projects", "load the X topic". Do…
obsidian-bases
Explain, draft, and validate Obsidian Bases .base files with filters, formulas, properties, summaries, and table, card, or list views. Use for Obsidian Bases, database-like vault views, dynamic tables, reading lists, task trackers, filters, formulas, summaries, and .base file edits.
save
Save a user-selected answer, decision, insight, or session summary into an Obsidian vault as one reviewed transaction. Use only when the user explicitly asks to preserve specific conversation content, not when they supply a file or URL to ingest. Triggers: /save, save this, save that answer, file this conversation…