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 skills add dhruv-anand-aintech/continue-later-skill --skill resume-from-earliergit clone --depth 1 https://github.com/dhruv-anand-aintech/continue-later-skillWrote 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/dhruv-anand-aintech/continue-later-skill/resume-from-earlier)<a href="https://agentmods.dev/skills/dhruv-anand-aintech/continue-later-skill/resume-from-earlier"><img src="https://agentmods.dev/badge/skills/dhruv-anand-aintech/continue-later-skill/resume-from-earlier/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.
<a href="https://agentmods.dev/skills/dhruv-anand-aintech/continue-later-skill/resume-from-earlier"><img src="https://agentmods.dev/badge/skills/dhruv-anand-aintech/continue-later-skill/resume-from-earlier.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00058 | $0.00782 |
| Opus 5 | $0.00029 | $0.00391 |
| Sonnet 5 | $0.00012 | $0.00156 |
| Haiku 4.5 | $0.00006 | $0.00078 |
Grade A, and why
resume-from-earlier 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.
How it starts
The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Resume From Earlier
Read and summarize project handoff markdown so work can resume quickly without losing context.
This is a separate skill folder from resume-continuation so assistants that only load skills by directory name (not a shared manifest) still pick up the slash-style command /resume-from-earlier. The workflow is identical to resume-continuation.
Files
| File | Typical source |
|---|---|
continuation.md |
Full structured handoff (continue-later skill) |
continuation-fast.md |
Raw git dump (+ optional transcript excerpts) from continue-later-fast |
Overview
Use this skill when the user says:
/resume-from-earlier(manual attach / slash command)- "resume from earlier"
- "resume from continuation"
- "what was I working on?"
- "continue from last session"
Natural-language variants without a slash are also covered by the resume-continuation skill; either skill may run for the same request.
Workflow
- Resolve which file(s) to read (project root):
- If
continuation.mdexists → treat it as the primary handoff (structured sections). - Else if
continuation-fast.mdexists → read it (often "## Raw Context Dump" / "## Recent user messages"). - If both exist → read
continuation.mdfirst for tasks/state/decisions/gotchas; then skimcontinuation-fast.mdonly when the user asks for the latest git snapshot, raw diff stats, or recent user prompts duplicated there—or when structured sections are missing. - If neither exists → say so and ask whether to create one (continue-later or continue-later-fast).
- If
- Extract only what the user asked for.
- Prefer these sections when present (mostly in structured
continuation.md):## Pending Tasksfor what to do next## Current Statefor working vs broken areas## Key Technical Decisionsto avoid re-litigating choices## Gotchas & Trapsto avoid repeated mistakes## How to Build & Runto restart quickly
Fromcontinuation-fast.md, surface## Raw Context Dump/### Recent user messageswhen relevant.
- Return a concise, actionable resume summary.
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.
- 11d ago First seen · 71 lines · 58 tokens per session scan A 2f3c6d1d862a
resume-from-earlier is a skill published in the GitHub repository dhruv-anand-aintech/continue-later-skill (3 stars, last pushed 3mo ago), licensed MIT. It adds 58 tokens to every session and 782 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 2026-08-31.
Other skills, from other repositories
karpathy-llm-wiki
Use when building or maintaining a personal LLM-powered knowledge base. Triggers: ingesting sources into a wiki, querying wiki knowledge, linting wiki quality, 'add to wiki', 'what do I know about', or any mention of 'LLM wiki' or 'Karpathy wiki'.
init
Install or update OwnMem in the current repository. Use when the user asks to set up OwnMem, add local project memory for coding agents, or refresh an existing OwnMem installation after a version bump.
memorix-sessions
Use when resuming work, preparing handoff context, binding an HTTP control-plane project, or deciding whether sessionstart is useful.
daily-journal
A passive daily work journal that Claude keeps FOR you so you never have to write it yourself. Append short entries after meaningful work (what was done, what you focused on, artifacts touched) to 01-daily/journal/YYYY-MM-DD.md. Run a guided reflection at night or in the morning. Use when you run /daily-journal, say…
doc-drift
Use this skill when the user wants to audit the memory and documents Claude Code loads into context — CLAUDE.md (user global + project + nested), MEMORY.md, @imports, .claude/skills, .claude/agents, .claude/commands, installed plugins — and detect four kinds of issues: outdated claims, mutually contradictory…
ijfw-handoff
Session handoff generation and loading. Trigger: session end, context full, /handoff.