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.
git clone --depth 1 https://github.com/5dive-ai/5dive-pluginsWrote 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/commands/5dive-ai/5dive-plugins/carryover)<a href="https://agentmods.dev/commands/5dive-ai/5dive-plugins/carryover"><img src="https://agentmods.dev/badge/commands/5dive-ai/5dive-plugins/carryover/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/commands/5dive-ai/5dive-plugins/carryover"><img src="https://agentmods.dev/badge/commands/5dive-ai/5dive-plugins/carryover.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 | $0.00014 | $0.00493 |
| Opus 5.5 | $0.00006 | $0.00197 |
| Sonnet 5.5 | $0.00003 | $0.00099 |
| Haiku 4.5 | $0.00001 | $0.00049 |
Grade A, and why
carryover 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 1mo 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.
What it actually says
/carryover — context carry-over
The current session's context window is filling up. Capture everything a fresh session would need so you can carry the thread over without losing it, then tell the user to start clean.
Write the carryover
Write a single carryover file into your memory directory (the same
.../memory/ folder your other memories live in), named
carryover_<YYYY-MM-DD>.md (use today's date; if one already exists,
overwrite it with the current state). Frontmatter:
---
name: carryover_<YYYY-MM-DD>
description: "SESSION CARRYOVER (<date> <time> UTC) — read FIRST on fresh start, then delete once caught up"
metadata:
type: project
---
Body — be concrete and specific, not generic. Include:
- Goal / what we're doing — the active task(s) and why, in 1-2 lines.
- State right now — what's done, what's in flight, what's verified vs not. Name exact files, commands, task IDs, commit SHAs, versions.
- Open threads — every loose end, numbered, with enough detail to resume blind. Include anything blocked on the user.
- Next step — the single most concrete thing to do first on resume.
- Channel — if paired over Telegram, note the chat_id so the new session knows how to reply.
End the body with a line telling the next session to delete this file and its
MEMORY.md pointer once it has caught up (it is a one-shot carryover, not a
permanent memory).
Then add a one-line pointer to MEMORY.md (- [SESSION CARRYOVER <date>](carryover_<date>.md) — READ FIRST if fresh).
Then tell the user
Confirm over their channel (Telegram reply if paired) in one short message:
the carryover is saved, and they can start a fresh session (/clear or a new
run) whenever — the next session auto-loads the carryover from memory and
picks up where this one left off. Do not start a new session yourself; leave
that to the user.
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.
- 1mo ago First seen · 51 lines · 14 tokens per session scan A dcb4ed55084f
carryover is a command published in the GitHub repository 5dive-ai/5dive-plugins (2 stars, last pushed today), licensed Apache-2.0. It adds 14 tokens to every session and 493 once invoked, about $0.0001 per session on Opus 5.5. 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 commands, from other repositories
learn
Force claude-smart to extract learnings from this session now.
recall-save
Generate / overwrite .recall/context.md with Recall's local offline summarizer.
notebook-query
Query the notebook knowledge base (SQLite) built by /agy:notebook — precise, grounded, cited. Ask in natural language ("sum the amounts by category", "which docs mention 'Acme Corp'", "build a project timeline") or pass raw SQL. Read-only. Use this when you need exact aggregates/lookups across a document corpus…
record
Record a browser walkthrough of a URL using Antigravity (agy). Generates .webm video, screenshots, and a report. Auto-converts to MP4 if ffmpeg is available.
ai-act-ask
Answer an EU AI Act question grounded in the bundled knowledge base — verbatim statute text, obligation paraphrases, and the compound-risk taxonomy. Offline and deterministic by default; cites the articles it relies on.
broadcast
Run broadcast on a distilled Raw — update related existing pages conversationally.