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 continue-later-fastgit 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/continue-later-fast)<a href="https://agentmods.dev/skills/dhruv-anand-aintech/continue-later-skill/continue-later-fast"><img src="https://agentmods.dev/badge/skills/dhruv-anand-aintech/continue-later-skill/continue-later-fast/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/continue-later-fast"><img src="https://agentmods.dev/badge/skills/dhruv-anand-aintech/continue-later-skill/continue-later-fast.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 | $0.00057 | $0.00664 |
| Opus 5.5 | $0.00023 | $0.00266 |
| Sonnet 5.5 | $0.00011 | $0.00133 |
| Haiku 4.5 | $0.00006 | $0.00066 |
Grade C, and why
continue-later-fast scanned grade C with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
After **`curl … | bash install`** (see repo README), the CLI bundle lives in **`${XDG_CONFIG_HOME:-~/.config}/continue-later/`** and a **`continue-later-fast`** symlink is added under **`${CONTINUE_LATER_BIN_DIR:-~/.loca Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
After **`curl … | bash install`** (see repo README), the CLI bundle lives in **`${XDG_CONFIG_HOME:-~/.config}/continue-later/`** and a **`continue-later-fast`** symlink is added under **`${CONTINUE_LATER_BIN_DIR:-~/.loca How it starts
The opening of the file, as written. The whole thing — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Continue Later Fast
Do this
After curl … | bash install (see repo README), the CLI bundle lives in ${XDG_CONFIG_HOME:-~/.config}/continue-later/ and a continue-later-fast symlink is added under ${CONTINUE_LATER_BIN_DIR:-~/.local/bin} (ensure that directory is on PATH). From any directory, cd to the git repository root of the project being handed off, then run:
continue-later-fast -n 12
Equivalent paths (no PATH needed):
"${XDG_CONFIG_HOME:-$HOME/.config}/continue-later/continue-later-fast.sh" -n 12
That script archives prior continuation.md / continuation-fast.md, writes continuation-fast.md, and appends recent user messages (newest local *.jsonl by mtime by default).
Developing in a clone of this repo you can run ./scripts/continue-later-fast.sh instead (same behavior; helpers must stay beside the wrapper).
Do not hand-roll inline git log / status / diff into continuation.md when the installed script exists.
Optional
| Flag / env | Purpose |
|---|---|
--agent <id> / CONTINUE_LATER_AGENT |
Pin a specific session JSONL |
--skip-transcript / CONTINUE_LATER_SKIP_TRANSCRIPT=1 |
Git snapshot only |
--from-cwd / CONTINUE_LATER_FROM_CWD=1 |
Prefer Claude transcript mentioning $PWD; else newest mtime |
-n / CONTINUE_LATER_LIMIT |
Max prompts (default 12) |
CONTINUE_LATER_CLI_DIR / CONTINUE_LATER_BIN_DIR |
Installer overrides for custom install locations |
Claude Code: If === CONTINUATION CONTEXT DUMP … === is already injected by the hook, you may still run continue-later-fast once to persist continuation-fast.md on disk.
Cursor: After install.sh, a beforeSubmitPrompt hook runs continue-later-fast on the same continuation-style phrases so continuation-fast.md is updated when you send the message (no prompt injection—disk only). Opt out of hook install with CONTINUE_LATER_CURSOR_HOOK=0.
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.
- 2mo ago First seen · 47 lines · 57 tokens per session scan C ff09bc1017fd
continue-later-fast is a skill published in the GitHub repository dhruv-anand-aintech/continue-later-skill (4 stars, last pushed 5mo ago), licensed MIT. It adds 57 tokens to every session and 664 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
continue-later-fast compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| continue-later-fastdhruv-anand-aintech/continue-later-skill | Skill | 4 | 5mo ago | MIT | C | 57 | Claude Code, Codex |
| git-advanced-workflowswshobson/agents | Skill | 43k | 6d ago | MIT | A | 54 | Claude Code |
| chinese-git-workflowjnMetaCode/superpowers-zh | Skill | 8.5k | today | MIT | A | 69 | Claude Code |
| workflow-patternswshobson/agents | Skill | 43k | 6d ago | MIT | A | 35 | Claude Code |
| dsh-pre-push-checksqufei1993/skills-hub | Skill | 1.9k | yesterday | MIT | A | 51 | Codex |
| devops/changelog-generationechoVic/boss-skill | Skill | 584 | 6d ago | MIT | A | 36 | Claude Code |
| managing-gitCloudAI-X/claude-workflow-v2 | Skill | 1.4k | 1mo ago | MIT | A | 46 | Claude Code |