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-batch-scope-diagnosegit clone --depth 1 https://github.com/Emasoft/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-batch-scope-diagnose)<a href="https://agentmods.dev/commands/emasoft/claude-plugins-validation/cpv-batch-scope-diagnose"><img src="https://agentmods.dev/badge/commands/emasoft/claude-plugins-validation/cpv-batch-scope-diagnose.svg" alt="Measured on agentmods" 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 | $0.00107 | $0.01753 |
| Opus 5 | $0.00053 | $0.00877 |
| Sonnet 5 | $0.00021 | $0.00351 |
| Haiku 4.5 | $0.00011 | $0.00175 |
Grade B, and why
cpv-batch-scope-diagnose 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 4d 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.
description: Read-only diagnostic across a fleet of project folders. One cpv-doctor-agent per project diagnoses the requested scope — user (~/.claude/), project (<project>/.claude/), local (<project>/.claude/settings.loc How it starts
The opening of the file, as written. The whole thing — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/cpv-batch-scope-diagnose — Read-only scope-aware diagnostic
The doctor's diagnostic surface includes three filesystem-anchored extension scopes:
| Scope | Surface |
|---|---|
user |
~/.claude/ — global agents/skills/MCP/hooks/output-styles/etc. |
project |
<project>/.claude/ — git-tracked entries |
local |
<project>/.claude/settings.local.json — gitignored local entries |
full |
All of the above + cross-scope conflict checker |
For users who operate across many project folders (a fleet), this
command runs the doctor in read-only mode on every one, in
parallel, and aggregates the per-project findings into a single
status table. URL inputs are forbidden — the doctor needs
~/.claude/ and <project>/.claude/ filesystem state.
You are the orchestrator
You — the model running THIS turn — drive the batch. You do NOT diagnose anything yourself.
Step 0 — Resolve arguments
If no project folder list was given, default to $PWD. If any
input looks URL-shaped, surface the canonical CRITICAL message:
ERROR: cpv-batch-scope-* skills require LOCAL project paths.
A valid Claude installation (~/.claude/) is necessary to
diagnose user/project/local-scope extensions. URL inputs
cannot reach the filesystem state of a Claude installation.
Use cpv-batch-validate or cpv-batch-security-audit for
source-tree scans of remote plugins.
…and stop.
Step 1 — Build the batch plan
BATCH_SPEC="${1:-$PWD}"
SCOPE="full" # or --scope override
MAX_PARALLEL=8
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/cpv_batch_orchestrator.py" plan \
"$BATCH_SPEC" \
--agent cpv-doctor-agent \
--mode batch_scope_diagnose \
--no-url \
--max-parallel "$MAX_PARALLEL"
Capture the orchestrator's stdout (PLAN, STATUS_TABLE,
SESSION_DIR, PLUGIN_COUNT, DISPATCH_GROUPS). You MUST bind
each into a shell variable from its KEY: line — the very next
command below references $STATUS_TABLE, and Steps 3-4 reference
$SESSION_DIR/plan.json for emit-status. If $SESSION_DIR is left
unbound it expands to the empty string and emit-status "/plan.json"
crashes (file not found). Queue the initial status table for the
claude-menu-system Stop hook (emitted post-turn via systemMessage —
zero token cost, NEVER printed inline by the orchestrator):
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.
- 4d ago First seen · 188 lines · 107 tokens per session scan B fd5ee7d917be
cpv-batch-scope-diagnose is a command published in the GitHub repository Emasoft/claude-plugins-validation (4 stars, last pushed yesterday), licensed MIT. It adds 107 tokens to every session and 1,753 once invoked, about $0.0005 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
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.