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/Cfvillarroel/carryoverWrote 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/cfvillarroel/carryover/inbox)<a href="https://agentmods.dev/commands/cfvillarroel/carryover/inbox"><img src="https://agentmods.dev/badge/commands/cfvillarroel/carryover/inbox/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/cfvillarroel/carryover/inbox"><img src="https://agentmods.dev/badge/commands/cfvillarroel/carryover/inbox.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 | $0.00009 | $0.00278 |
| Opus 5 | $0.00005 | $0.00139 |
| Sonnet 5 | $0.00002 | $0.00056 |
| Haiku 4.5 | $0.00001 | $0.00028 |
Grade A, and why
inbox scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Show the messages other Conductor workspaces have left for this one. Run via Bash:
PY="$HOME/.headroom/venv/bin/python"; [ -x "$PY" ] || PY="$(command -v python3)"
"$PY" "$HOME/.carryover/co-mem" inbox --peek
That lists pending messages without consuming them (each item has a from and content).
Present them clearly. If the user wants to mark them as read (so they don't show again), run the
same command without --peek.
Note: the auto-delivery hooks (session start / end of turn) already consume incoming messages
as they surface them into context — so --peek will often be empty even right after a message
arrived. To re-read a message that was already delivered (e.g. it got truncated in context, or
context was compacted), run with --all, which also lists already-delivered messages and never
consumes:
PY="$HOME/.headroom/venv/bin/python"; [ -x "$PY" ] || PY="$(command -v python3)"
"$PY" "$HOME/.carryover/co-mem" inbox --all
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.
- 9d ago First seen · 26 lines · 9 tokens per session scan A 8de80737a756
inbox is a command published in the GitHub repository Cfvillarroel/carryover (5 stars, last pushed 24d ago), licensed MIT. It adds 9 tokens to every session and 278 once invoked, about $0.0000 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 commands, from other repositories
compiling-project-guidelines
Compile scattered guideline sources into one scope-aware COMPILED-GUIDELINES.md for other skills and ult-context-generate's Constraints layer. Do NOT use to enforce rules at runtime.
handoff
Generate a compact cross-tool handoff block from current session state.
gtd
A main entry point for a Getting Things Done (GTD) task-management workflow. GTD is a method for capturing tasks, clarifying what they mean, organizing them, choosing what to do, and reviewing the system.
gtd-capture
A command for capturing tasks, ideas, and reminders into an inbox before organizing them. GTD, or Getting Things Done, is a task-management method that separates collecting items from deciding what they mean and where they belong.
gtd-organize
A command that checks the structure of a GTD task system, including orphaned, stalled, duplicated, or incorrectly organised items.
gtd-review
A command for performing a weekly review of a GTD task system, including a preparation summary and checks of current commitments and longer-term direction.