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 Emasoft/claude-plugins-validation/plugin install claude-plugins-validationWrote 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/emasoft/claude-plugins-validation/cpv-main-menu)<a href="https://agentmods.dev/commands/emasoft/claude-plugins-validation/cpv-main-menu"><img src="https://agentmods.dev/badge/commands/emasoft/claude-plugins-validation/cpv-main-menu/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/emasoft/claude-plugins-validation/cpv-main-menu"><img src="https://agentmods.dev/badge/commands/emasoft/claude-plugins-validation/cpv-main-menu.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 | $0.00036 | $0.01044 |
| Opus 5.5 | $0.00014 | $0.00418 |
| Sonnet 5.5 | $0.00007 | $0.00209 |
| Haiku 4.5 | $0.00004 | $0.00104 |
Grade A, and why
cpv-main-menu scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/cpv-main-menu — CPV Main Menu
One inline entry point to every CPV command, skill, and agent, shown as a
post-turn Stop-hook menu (rendered via systemMessage, so it never enters
the transcript or prompt cache). Every menu has a 0 — Cancel / Exit row;
sub-menus also have B — Back.
The full menu tree AND the fixed key→action routing map are the single source
of truth in
menu-tree.md
(cpv-main-menu-skill, auto-loaded). Do NOT restate the menu rows or the key
map here — read them there.
Categories (the top menu — full rows + routing live in menu-tree.md)
Validate · Fix · Optimize for Cache · Diagnose · Update ·
Create · Publish & Migrate · Manage — plus H (Help / About),
A (Ask the agent), 0 (Cancel / Exit).
Workflow (runs inline in the main session — no subagent fork)
- Queue the top menu. One Bash call: export
CPV_SKILL_MENUS_DIRto the skill'sskill-menus/dir, thenpython "${CLAUDE_PLUGIN_ROOT}/scripts/print_menu.py" fixed 5 >/dev/null 2>&1(loads the pre-bakedskill-menus/05-main.json). Then END THE TURN emitting ZERO chat text — theclaude-menu-systemStop hook renders the menu viasystemMessage, so it costs no context. NEVER print the menu inline; NEVER use Write/Edit to stage a spec (print_menu.pyloads it by index — that is why the Bash card stays tiny and silent). - Wait for the user's key (number or letter, case-insensitive).
0at any level → replyCancelled — no actions taken.and stop.Bin a sub-menu → re-queue the parent menu.- Category key → look up its
action_idinmenu-tree.md, run that sub-menu's heredoc recipe, and end the turn silently. - Leaf key → ask any required arguments as plain-text questions, then
execute that command's workflow inline (read its
.md, run its bash) — actually run it, don't just name it. Every validator call goes throughpython "${CLAUDE_PLUGIN_ROOT}/scripts/remote_validation.py" <alias>— never the plugin-cache scripts directly. - Report the compact summary + report-file path, then run the §3.99 "do
something else?" heredoc (or the §3.10 post-validate menu for Validate
leaves) and end silently.
0→Done.
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 · 81 lines · 36 tokens per session scan A a13284d30a51
cpv-main-menu is a command published in the GitHub repository Emasoft/claude-plugins-validation (4 stars, last pushed 3d ago), licensed MIT. It adds 36 tokens to every session and 1,044 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
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
speckit.bug.fix
Apply the remediation from a bug assessment and record what was changed.