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/emasoft/claude-plugins-validation/cpv-agentgit clone --depth 1 https://github.com/Emasoft/claude-plugins-validationWhat 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 | $0.00073 | $0.00504 |
| Opus 5 | $0.00036 | $0.00252 |
| Sonnet 5 | $0.00015 | $0.00101 |
| Haiku 4.5 | $0.00007 | $0.00050 |
Grade A, and why
cpv-agent 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 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.
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
/cpv-agent — free-form CPV worker (direct dispatch)
$ARGUMENTS is a free-form plugin-quality request. Hand it verbatim to the
claude-plugins-validation:cpv-agent subagent, which reads the intent-to-action
map in cpv-the-skills-menu and autonomously routes the request to the right CPV
skill, agent, or script, running the whole job in its own isolated context (so the
verbose per-file work never enters this session).
This is the direct-slash shortcut to the same worker the main menu reaches via its
A — Ask the agent row. Use it when you already know you want the CPV agent and do
not want to open the menu first.
Workflow
- If
$ARGUMENTSis empty, ask the user what CPV task they want, then stop. - Otherwise dispatch ONE
claude-plugins-validation:cpv-agentsubagent via the Agent tool, passing$ARGUMENTSas the task. The default target is the current plugin unless the request names another path or GitHub URL. For substantive or multi-file work the subagent may itself fan out to specialised CPV work agents (cpv-plugin-fixer-agent,cpv-cache-optimizer-agent, and the like). - Relay the subagent's final one-line result and the path to the report it wrote
under
reports/.
Notes
- The
cpv-agentsubagent is also dispatchable directly by other agents assubagent_type: claude-plugins-validation:cpv-agent— this command only adds the user-facing/cpv-agentslash surface on top of that existing agent. - For one bounded edit prefer
cpv-spark-agent; for an interactive numbered menu use/cpv-main-menu.
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 · 38 lines · 73 tokens per session scan A 7ee4b8648b12
cpv-agent is a command published in the GitHub repository Emasoft/claude-plugins-validation (4 stars, last pushed 4d ago), licensed MIT. It adds 73 tokens to every session and 504 once invoked, about $0.0004 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
git
Git operations with intelligent commit messages and workflow optimization.
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.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
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.