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/trueclicks/claude-plugins/get-customgit clone --depth 1 https://github.com/TrueClicks/claude-pluginsWhat 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 | $0.00000 | $0.00471 |
| Opus 5 | $0.00000 | $0.00235 |
| Sonnet 5 | $0.00000 | $0.00094 |
| Haiku 4.5 | $0.00000 | $0.00047 |
Grade A, and why
get-custom scanned grade A 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 yesterday.
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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
mkdir -p tmp && curl -s --max-time 230 -o tmp/response.zip -D tmp/response_headers.txt -X POST "https://api.claudeppc.ai/api/cli/google-ads/get-custom-data?pluginVersion=1.8.0" -F "[email protected]" -F "name={query_na What it actually says
Fetch Custom Google Ads Data
Runs a custom GAQL query to fetch data not available in the standard export.
When to Use
Use this when the data in data/account/ and data/performance/ is insufficient and you need:
- Different date ranges
- Metrics not included in the standard export
- Data at different aggregation levels
- Specific segments or filters
Steps
-
Construct a valid GAQL query for the data needed.
-
Run the following command (set Bash timeout to 240000ms — the server may take up to 230 seconds), substituting the query parameters:
mkdir -p tmp && curl -s --max-time 230 -o tmp/response.zip -D tmp/response_headers.txt -X POST "https://api.claudeppc.ai/api/cli/google-ads/get-custom-data?pluginVersion=1.8.0" -F "[email protected]" -F "name={query_name}" -F "query={GAQL query}"
Check tmp/response_headers.txt for a line starting with X-Plugin-Update:. If found, display its value to the user as a notice. Then delete the headers file: rm -f tmp/response_headers.txt.
Parameters:
name: Short identifier for the query (e.g.,campaign_7d,keyword_device). Used as the output filename.query: Valid GAQL query string (e.g.,SELECT campaign.name, metrics.clicks FROM campaign)
- Extract and clean up:
mkdir -p data/custom && unzip -o tmp/response.zip -d data/custom && rm tmp/response.zip
- Read the results file
data/custom/<query_name>.mdand present the data to the user.
Example
Query name: top_keywords
GAQL: SELECT ad_group_criterion.keyword.text, metrics.conversions FROM keyword_view WHERE metrics.conversions > 0 ORDER BY metrics.conversions DESC LIMIT 50
Notes
- Monetary values in GAQL results are in micros (divide by 1,000,000 for currency)
- Results are saved as markdown tables
- Multiple custom queries can coexist in
data/custom/
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.
- yesterday First seen · 46 lines · 0 tokens per session scan A a4350309ef8c
get-custom is a command published in the GitHub repository TrueClicks/claude-plugins (2 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 471 tokens. A static security scan graded it A with 1 finding (makes network calls). 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.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
constitution
Create or update the project constitution from interactive or provided principle inputs.
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.