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 mtarcure/claude-vibe-squad --skill compact-nowgit clone --depth 1 https://github.com/mtarcure/claude-vibe-squadWrote 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/mtarcure/claude-vibe-squad/compact-now)<a href="https://agentmods.dev/skills/mtarcure/claude-vibe-squad/compact-now"><img src="https://agentmods.dev/badge/skills/mtarcure/claude-vibe-squad/compact-now/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/mtarcure/claude-vibe-squad/compact-now"><img src="https://agentmods.dev/badge/skills/mtarcure/claude-vibe-squad/compact-now.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00082 | $0.01461 |
| Opus 5.5 | $0.00033 | $0.00584 |
| Sonnet 5.5 | $0.00016 | $0.00292 |
| Haiku 4.5 | $0.00008 | $0.00146 |
Grade A, and why
compact-now 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.
How it starts
The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/compact-now
Chrono-side proactive compaction. The operator triggers via slash phrase. Chrono:
- Reads the live board partition via
chrono_state.registry.registry_view()and confirms no live work is in flight. Whether context pressure warrants compacting is Chrono's judgment againstshared/lifecycle.md§ 8. The context tripwire hook (bin/context-tripwire.sh) already reports the measured token count on every prompt once it passes 400k, so a WARN/HARD line in the current turn is the direct signal; below that, pressure is inferred from the § 9 proxy signals. - If blockers exist (live dispatches), surfaces them to the operator and asks whether to proceed anyway — likewise for any unclassified registry status, which the partition cannot vouch for.
- Externalizes load-bearing state to the Vault via the current
record("learning", {...})writer — captures active decisions (authority), open tasks, pending approvals, and the next action. - Snapshots the same state to
_state/chrono/compaction/<session>.jsonviachrono_state.compaction.snapshot(). - Invokes Claude Code's native
/compact. - After compact, reads the snapshot via
chrono_state.compaction.recover()and re-anchors on the next operator turn — never bulk-re-reading conversation history.
When to invoke
- Operator types
/compact-now(explicit) - Operator types
compact now/please compact/let's compactin prose (intent-recognition) - After Chrono has flagged context pressure against
shared/lifecycle.md§ 8 and the operator nudges affirmatively
When NOT to invoke
- Live dispatches running (
registry_view()["live"]non-empty) — surface blockers first - Mid-task (Chrono still processing) — wait for a task boundary
- Below the
shared/lifecycle.md§ 8 threshold — no benefit, just cost
Implementation
Chrono runs this skill inline (not a subagent dispatch), operator-triggered. It uses the
chrono_state helpers (in scripts/python/chrono_state/) and Chrono's existing chrono-vault
MCP access. A PreCompact hook is OPTIONAL and only fires if .claude/settings.json declares
one — do not depend on it; externalize eagerly here.
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 Changed · +2 lines 0dc1303cd393
- 1mo ago First seen · 114 lines · 82 tokens per session scan A 57bd8897ef29
compact-now is a skill published in the GitHub repository mtarcure/claude-vibe-squad (164 stars, last pushed 1mo ago), licensed MIT. It adds 82 tokens to every session and 1,461 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
handoff
Write a compact, decision-ready handoff so the next session (or the user) can continue without reconstructing the current one. Use when the session is ending, context is running low, the user asks for a handoff / 'pass the baton' / 'hand off', or a long-running operation needs a durable state checkpoint.
gmail
Search, read, draft, and send Gmail when the user asks to work with their inbox or email.
google-calendar
Read schedules, check availability, and create or update Google Calendar events when the user asks to work with their calendar.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
openrig-herdr
Use when opening OpenRig fleet terminals as a herdr wall — turning a rig, pod, mission, slice, or saved view into live interactive agent tiles via rig terminal, watching another rig read-only, or driving herdr on an agent's request ("open all my rigs + a mission as views"). Covers the rig terminal open|views|status…
forget
Help the user remove a stored fact using Codewhale's Context Lens when they ask to forget or delete a memory.