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 agentmods add commands/msshives-gif/claude-plugins/statusgit clone --depth 1 https://github.com/msshives-gif/claude-pluginsWhat 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 | $0.00012 | $0.00603 |
| Opus 5 | $0.00006 | $0.00302 |
| Sonnet 5 | $0.00002 | $0.00121 |
| Haiku 4.5 | $0.00001 | $0.00060 |
Grade B, and why
status 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 2d 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
Report the current compact-manager state.
- 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
${CLAUDE_PLUGIN_ROOT}literally — plugin installs may not substitute command markdown — find the CLI file itself:find ~/.claude/plugins -maxdepth 8 -type f -name compact-manager -path "*/bin/*" 2>/dev/null(this handles versioned cache layouts, where a directory merely NAMED compact-manager has no bin/). If several paths match, use the most recently modified (ls -t). - Run
"${CLAUDE_PLUGIN_ROOT}/bin/compact-manager" overviewand relay its output verbatim in a code block. The logic (window resolution, attention flags, current-session marker) lives in the CLI, not here — do not re-derive it. - Add ONE line of interpretation for the
>-marked session row: its usage percentage and whether a watcher holds it. (>is a recency heuristic — check itsupdatedage; seconds-old means it is almost certainly the invoking session.) Any row flaggedATTENTION,DEAD-LEASE, orMALFORMED-LEASEneeds the human's eyes — lead with those. (Raw JSON, if needed: thestatussubcommand.) Note: the start-of-session status line uses stricter positive-proof attachment than the overview's conservativeliveflag, so the two can disagree on a malformed lease. TheMALFORMED-LEASEflag catches pid-malformed shapes on rows that surface as live; it cannot see an empty lease file (no row is produced at all), a dead lease's pid shape (flaggedDEAD-LEASEinstead), or fields the row does not carry (token, start time, heartbeat). A watcher row withreason=session_rotatedmeans the pane's session id changed under it (/clearor in-app/resume) and it retired cleanly — suggest re-attaching if the user wants the pane's current session watched. The sessions table'salivecolumn is the CLI's own verdict (registry + /proc proof) — relay it, don't re-derive:GONEmeans the session's claude process is no longer running and the row is just its state file aging out (≤24h);?means liveness could not be judged on this machine. AGONErow is normal housekeeping, not something to alert on.
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.
- 2d ago First seen · 43 lines · 12 tokens per session scan B 87895b7eaa64
status is a command published in the GitHub repository msshives-gif/claude-plugins (2 stars, last pushed 6d ago), licensed MIT. It adds 12 tokens to every session and 603 once invoked, about $0.0001 per session on Opus 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
check-best-practices
Analyze code against language-specific best practices, coding standards, and community conventions to improve code quality and maintainability.
test-basic-role-override
Test Type: Fundamental prompt injection detection Risk Level: High Expected Detection: Role manipulation attempts.
VibeGuard: Cross Review
Dual-model adversarial review — Claude generates review reports, Codex does adversarial verification, and iterates until convergence.
VibeGuard: Preflight
Explore the project before major modifications, generate constraint sets, and prevent problems from the source.
VibeGuard: Review
Structured code review - first run the guard to obtain the baseline, then review according to security → logic → quality → performance priority.
VibeGuard: Build Fix
Build repair — read build errors, locate root causes, perform minimal repairs, and verify that the build passed.