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.
git clone --depth 1 https://github.com/lckx777/copy-chief-blackWrote 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/lckx777/copy-chief-black/validate-batch)<a href="https://agentmods.dev/commands/lckx777/copy-chief-black/validate-batch"><img src="https://agentmods.dev/badge/commands/lckx777/copy-chief-black/validate-batch/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/lckx777/copy-chief-black/validate-batch"><img src="https://agentmods.dev/badge/commands/lckx777/copy-chief-black/validate-batch.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 | $0.00019 | $0.01928 |
| Opus 5 | $0.00010 | $0.00964 |
| Sonnet 5 | $0.00004 | $0.00386 |
| Haiku 4.5 | $0.00002 | $0.00193 |
Grade B, and why
validate-batch scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
OFFER=$(cat ~/.claude/session-state/current-offer.json 2>/dev/null | grep -oP '"offer":\s*"\K[^"]+') How it starts
The opening of the file, as written. The whole thing — 232 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/validate-batch — Batch Validation Command
Validates all units of a deliverable (VSL chapters, LP blocks, creatives, emails) in parallel using subagents, then aggregates results with outlier detection.
S32 Integration: After collecting MCP scores, each unit is also scored with
quality-score.tsto produce a unified Quality Score (0-10) with per-deliverable weights. The batch summary includes mean Quality Score and flags units below 7.0.
Usage
/validate-batch <type> [--offer <name>] [--format yaml|json|md]
Types
| Type | Units | Validation |
|---|---|---|
vsl |
All VSL chapters | blind_critic + emotional_stress_test |
lp |
All LP blocks (14) | blind_critic |
creatives |
All creatives | blind_critic + emotional_stress_test |
emails |
All emails in sequence | blind_critic |
Process
Step 1: Detect Offer
# Resolve offer from $ARGUMENTS or current context
ARGS="$ARGUMENTS"
# Extract --offer flag if present
if echo "$ARGS" | grep -q "\-\-offer"; then
OFFER=$(echo "$ARGS" | grep -oP '\-\-offer\s+\K\S+')
else
# Detect from current-offer.json
OFFER=$(cat ~/.claude/session-state/current-offer.json 2>/dev/null | grep -oP '"offer":\s*"\K[^"]+')
fi
TYPE=$(echo "$ARGS" | awk '{print $1}')
echo "Offer: $OFFER | Type: $TYPE"
If offer cannot be detected, stop and ask the user.
Step 2: Scan for Deliverable Files
# Determine scan path by type
case "$TYPE" in
vsl) SCAN_PATH="*/production/vsl/" ;;
lp) SCAN_PATH="*/production/landing-page/blocks/" ;;
creatives) SCAN_PATH="*/production/creatives/" ;;
emails) SCAN_PATH="*/production/emails/" ;;
*) echo "Unknown type: $TYPE"; exit 1 ;;
esac
find ~/copywriting-ecosystem -path "*/$OFFER/$SCAN_PATH*.md" -type f | sort
If no files are found, report clearly and stop.
Step 3: Dispatch Parallel Subagents
For each file found, dispatch a general-purpose subagent to run the appropriate validation
MCPs. Run all subagents in parallel (max 6 concurrent — see ~/.claude/config/batch-validation.yaml).
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.
- 7d ago First seen · 232 lines · 19 tokens per session scan B 03a69f058a50
validate-batch is a command published in the GitHub repository lckx777/copy-chief-black (5 stars, last pushed 6mo ago), licensed MIT. It adds 19 tokens to every session and 1,928 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 2026-09-03.
Other commands, from other repositories
prototype
You are building a proof-of-concept for the current Grainulator sprint. Read CLAUDE.md for sprint context and claims.json for existing research claims.
verify
Run repository verification using the verification-loop skill.
qa-changes
This skill should be used when the user asks to "QA a pull request", "test PR changes", "verify a PR works", "functionally test changes", or when an automated workflow triggers QA validation of code changes. Provides a structured methodology for setting up the environment, exercising changed behavior, and reporting…
test-coverage
Analyze test coverage and identify the highest-value gaps to fill.
tdd
A command that follows test-driven development (TDD), a method where you write tests before the code they check. It moves through writing a failing test, adding the smallest implementation, and then improving the code.
check-dev
Type-check a Z specification with fuzz.