Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add msshives-gif/claude-plugins/plugin install compact-managerWrote 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/msshives-gif/claude-plugins/attach)<a href="https://agentmods.dev/commands/msshives-gif/claude-plugins/attach"><img src="https://agentmods.dev/badge/commands/msshives-gif/claude-plugins/attach/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/msshives-gif/claude-plugins/attach"><img src="https://agentmods.dev/badge/commands/msshives-gif/claude-plugins/attach.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 | $0.00012 | $0.00427 |
| Opus 5.5 | $0.00005 | $0.00171 |
| Sonnet 5.5 | $0.00002 | $0.00085 |
| Haiku 4.5 | $0.00001 | $0.00043 |
Grade B, and why
attach scanned grade B with 1 finding 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
itself: `find ~/.claude/plugins -maxdepth 8 -type f -name What it actually says
Attach the compact-manager watcher to the current Claude Code session so
/compact gets typed automatically at the configured threshold (managed
mode).
- Locate the compact-manager CLI. The path in the later steps
normally reads as an absolute path (script installs write it in).
If it instead still says
${CLAUDE_PLUGIN_ROOT}literally — plugin installs may not substitute command markdown — find the CLI file itself:find ~/.claude/plugins -maxdepth 8 -type f -name compact-manager -path "*/bin/*" 2>/dev/null(this handles versioned cache layouts, where a directory merely NAMED compact-manager has no bin/). If several paths match, use the most recently modified (ls -t). - Check the pane: run
echo "$TMUX_PANE"in your shell tool. If it is empty, this session is not running under tmux — managed mode requires tmux. Report that and stop. - Run:
"${CLAUDE_PLUGIN_ROOT}/bin/compact-manager" adopt -t "$TMUX_PANE" --attended - Interpret the result:
- Success (prints
watcher pid=… run_token=…): confirm with theoverviewsubcommand and report this session's watcher state. - A lease error (
lease_heldor similar): a live watcher already holds this session or pane — report that it was already attached, with theoverviewoutput. - Any other error: report it verbatim. Do not retry in a loop.
- Success (prints
- If the configured mode is not
managed(config file~/.claude/compact-manager.json, envCOMPACT_MANAGER_MODE), the hooks will not cooperate with the watcher: tell the user to set{"mode": "managed"}there first.
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 · 34 lines · 12 tokens per session scan B be2790ed2c19
attach is a command published in the GitHub repository msshives-gif/claude-plugins (2 stars, last pushed 7d ago), licensed MIT. It adds 12 tokens to every session and 427 once invoked, about $0.0000 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
init
First-time Archcore setup — wire host configs, measure the authored context, compose the full first-day seed in one preview, and create it on one confirm; import converts CLAUDE.md, AGENTS.md, rule files, ADRs, and docs into native documents; refresh adds new facts or drills into one domain.
document
Record the present state by mode — decision (ADR, RFC, rule), code (spec, doc, guide, scenario), or research (a ready report or one external material); a gate picks the document type.
mainframe-tickets-verify
This is a user-invocable command. Execute it only because the current invocation explicitly selected it. It takes no arguments: every invocation processes the complete current project queue awaiting independent verification.
lint-status
Show AgentLint status — coverage, effective policy, session activity.
edit
An interview-style command for editing the trigger words used by existing personas. Personas are predefined viewpoints, such as a developer, designer, or lawyer, that guide how work is approached.
update
Update Slime to the latest version.