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 skills add dr-robert-li/cowork-wordpress-expert --skill build-modifygit clone --depth 1 https://github.com/dr-robert-li/cowork-wordpress-expertWrote 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/skills/dr-robert-li/cowork-wordpress-expert/build-modify)<a href="https://agentmods.dev/skills/dr-robert-li/cowork-wordpress-expert/build-modify"><img src="https://agentmods.dev/badge/skills/dr-robert-li/cowork-wordpress-expert/build-modify/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/skills/dr-robert-li/cowork-wordpress-expert/build-modify"><img src="https://agentmods.dev/badge/skills/dr-robert-li/cowork-wordpress-expert/build-modify.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 | $0.09366 |
| Opus 5.5 | $0.00014 | $0.03746 |
| Sonnet 5.5 | $0.00007 | $0.01873 |
| Haiku 4.5 | $0.00004 | $0.00937 |
Grade A, and why
build-modify 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 — 1,025 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Build Modify Skill
Session-aware execution engine for the /modify command. COMMAND.md owns the interactive session loop and invokes this skill's sections per step. Each atomic modification step produces its own git commit and build.json entry. No zip or SETUP.md regeneration occurs per step — those are deferred to session completion (Section 7).
This skill expects the following variables to be set by the calling command (/modify) before invocation:
| Variable | Source | Description |
|---|---|---|
WP_DIR |
/modify argument | Path to WordPress directory (set once at session start) |
MODIFY_MODE |
/modify session loop | "nl" for natural language, "visual" for design re-export (set per step) |
NL_REQUEST |
/modify session loop | Natural language modification request (set per NL step) |
VISUAL_PATH |
/modify session loop | Path to updated design export directory (set per visual step) |
Section 0: Prerequisites and Setup
Set up lazy Docker/WP-CLI helpers, declare the git_commit_stage helper function, and register an EXIT trap for MySQL container cleanup. Docker is NOT checked upfront — it is started lazily only when a content or plugin step requires MySQL.
# ── Lazy Docker/WP-CLI helpers ───────────────────────────────────────────────
# Docker and WP-CLI are only needed for content and plugin steps.
# Theme-only sessions (theme-token, template-edit) work without Docker entirely.
WP_CLI_MODE=""
WP=""
DOCKER_CHECKED=false
ensure_wp_cli() {
if [ "$DOCKER_CHECKED" = "true" ]; then
return 0
fi
# Check Docker is running
if ! docker info > /dev/null 2>&1; then
echo "[Modify] ERROR: Docker is required for content and plugin modifications."
echo "[Modify] Start Docker Desktop and try again."
echo "[Modify] Theme-only modifications (theme-token, template-edit) work without Docker."
return 1
fi
# Check for local WP-CLI first (preferred), Docker fallback
if which wp > /dev/null 2>&1; then
WP_CLI_MODE="local"
WP="wp --path=$BUILD_DIR"
echo "[Modify] WP-CLI ready (local)"
else
if docker run --rm wordpress:cli wp --version > /dev/null 2>&1; then
WP_CLI_MODE="docker"
WP="docker run --rm -v \"$BUILD_DIR:/var/www/html\" --network host wordpress:cli wp --allow-root"
echo "[Modify] WP-CLI ready (docker)"
else
echo "[Modify] ERROR: WP-CLI is required for content/plugin modifications but was not found."
return 1
fi
fi
DOCKER_CHECKED=true
return 0
}
ensure_docker_mysql() {
# Ensure WP-CLI is available first
if ! ensure_wp_cli; then
STEP_SKIPPED=true
return 1
fi
# Check database.sql exists
if [ ! -f "$BUILD_DIR/database.sql" ]; then
echo "[Modify] ERROR: database.sql not found in build directory."
echo "[Modify] Cannot perform content modifications without a database."
echo "[Modify] Theme-only modifications (theme-token, template-edit) are still possible."
STEP_SKIPPED=true
return 1
fi
# If MySQL is already running, reuse it
if [ "$MYSQL_RUNNING" = "true" ]; then
return 0
fi
# Read existing credentials from wp-config.php
EXISTING_DB_PASS=$($WP config get DB_PASSWORD 2>/dev/null || echo "")
EXISTING_DB_USER=$($WP config get DB_USER 2>/dev/null || echo "wp")
if [ -z "$EXISTING_DB_PASS" ]; then
EXISTING_DB_PASS="$(openssl rand -hex 12)"
EXISTING_DB_USER="wp"
echo "[Modify] NOTE: Could not read existing DB credentials — using generated credentials"
fi
# Port 3307 conflict check
if lsof -i :3307 > /dev/null 2>&1; then
echo "[Modify] ERROR: Port 3307 is already in use. Close the conflicting process and try again."
STEP_SKIPPED=true
return 1
fi
MYSQL_ROOT_PASS="wpmod_root_$(openssl rand -hex 8)"
# Start MySQL container with credentials matching wp-config.php
docker run -d \
--name "$MYSQL_CONTAINER" \
-e MYSQL_ROOT_PASSWORD="$MYSQL_ROOT_PASS" \
-e MYSQL_DATABASE=wordpress \
-e MYSQL_USER="$EXISTING_DB_USER" \
-e MYSQL_PASSWORD="$EXISTING_DB_PASS" \
-p 127.0.0.1:3307:3306 \
mysql:8.0 \
--default-authentication-plugin=mysql_native_password \
> /dev/null
MYSQL_RUNNING=true
echo "[Modify] Starting MySQL container..."
# Wait for ready (up to 30 seconds)
WAIT_COUNT=0
until docker exec "$MYSQL_CONTAINER" mysqladmin ping --silent 2>/dev/null; do
WAIT_COUNT=$((WAIT_COUNT + 1))
if [ "$WAIT_COUNT" -ge 30 ]; then
echo "[Modify] ERROR: MySQL container failed to start within 30 seconds."
STEP_SKIPPED=true
return 1
fi
sleep 1
done
echo "[Modify] Database ready."
# Import existing database.sql
if ! $WP db import "$BUILD_DIR/database.sql" 2>&1; then
echo "[Modify] ERROR: Database import failed. Cannot proceed with content modification."
STEP_SKIPPED=true
return 1
fi
echo "[Modify] Database imported into ephemeral container."
return 0
}
# ── MySQL container EXIT trap ────────────────────────────────────────────────
MYSQL_CONTAINER="wpmodify-mysql-$$"
MYSQL_RUNNING=false
cleanup_modify_mysql() {
if [ "$MYSQL_RUNNING" = "true" ]; then
echo "[Modify] Cleaning up Docker MySQL container..."
docker rm -f "$MYSQL_CONTAINER" 2>/dev/null || true
echo "[Modify] MySQL cleanup complete."
fi
}
trap cleanup_modify_mysql EXIT
# ── git_commit_stage function ────────────────────────────────────────────────
# Redeclared from build-git Section 4 — skills are separate execution contexts.
# Usage: git_commit_stage "commit subject" ["commit body"]
# Failures are warn-and-continue — git failures never abort the modification.
git_commit_stage() {
local SUBJECT="$1"
local BODY="${2:-}"
if [ "${GIT_INITIALIZED:-true}" != "true" ]; then
echo "[Modify] WARNING: Git not initialized — skipping commit: $SUBJECT"
return 0
fi
echo "[Modify] Git commit: $SUBJECT"
# Stage all changes
if ! git -C "$BUILD_DIR" add -A > /dev/null 2>&1; then
echo "[Modify] WARNING: git add failed for commit: $SUBJECT"
return 0
fi
# Check if there is anything to commit
if git -C "$BUILD_DIR" diff --cached --quiet 2>/dev/null; then
echo "[Modify] NOTE: Nothing to commit for: $SUBJECT (no changes staged)"
return 0
fi
# Commit — use -m twice for multiline commits (subject + body)
if [ -n "$BODY" ]; then
if git -C "$BUILD_DIR" commit -m "$SUBJECT" -m "$BODY" > /dev/null 2>&1; then
echo "[Modify] Committed: $SUBJECT"
else
echo "[Modify] WARNING: git commit failed for: $SUBJECT"
fi
else
if git -C "$BUILD_DIR" commit -m "$SUBJECT" > /dev/null 2>&1; then
echo "[Modify] Committed: $SUBJECT"
else
echo "[Modify] WARNING: git commit failed for: $SUBJECT"
fi
fi
echo ""
}
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 · 1,025 lines · 36 tokens per session scan A 3955928d09b4
build-modify is a skill published in the GitHub repository dr-robert-li/cowork-wordpress-expert (29 stars, last pushed 8mo ago), licensed MIT. It adds 36 tokens to every session and 9,366 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 2026-08-30.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…