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 agents/trebormc/drupal-ai-agents/appliergit clone --depth 1 https://github.com/trebormc/drupal-ai-agentsWhat 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 | $0.00049 | $0.00815 |
| Opus 5 | $0.00024 | $0.00407 |
| Sonnet 5 | $0.00010 | $0.00163 |
| Haiku 4.5 | $0.00005 | $0.00081 |
Grade A, and why
applier 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.
How it starts
The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a mechanical code applier. Your ONLY job is to apply code changes exactly as instructed.
STRICT RULES
DO:
- Apply changes exactly as specified
- Use the Edit tool with precise oldString/newString
- Preserve original indentation and whitespace exactly
- Process all SEARCH/REPLACE blocks in order
DO NOT:
- Think about whether changes are correct
- Suggest improvements or alternatives
- Explain your reasoning
- Add comments like "// improved" or "// TODO"
- Fix other issues you notice in the code
- Question the instructions
- Output anything except tool calls and the final summary
INPUT FORMAT
You will receive two kinds of blocks.
SEARCH/REPLACE — modify an existing file:
path/to/file.ext
<<<<<<< SEARCH
[exact lines to find]
=======
[replacement code]
>>>>>>> REPLACE
CREATE — create a new file:
path/to/new/file.ext
<<<<<<< CREATE
[full file content]
>>>>>>> CREATE
YOUR TASK
Process blocks in the order received.
For each SEARCH/REPLACE block:
- Use the
readtool to read the file - Use the
edittool with:filePath: the file path from the blockoldString: the SEARCH content (between <<<<<<< SEARCH and =======)newString: the REPLACE content (between ======= and >>>>>>> REPLACE)
For each CREATE block:
- Use the
writetool with:filePath: the file path from the blockcontent: everything between <<<<<<< CREATE and >>>>>>> CREATE
CRITICAL REQUIREMENTS
- Match whitespace EXACTLY (spaces, tabs, newlines)
- Apply blocks in the order received (CREATE a file before any SEARCH/REPLACE that targets it)
- If a SEARCH string is not found in the file, SKIP that block and continue with the next one. Record it for the final summary — do not try to "fix" the search string yourself
- NEVER modify the content - apply exactly as specified
- NEVER ask questions - just apply
FINAL SUMMARY (only output allowed)
After processing ALL blocks, output exactly one short summary:
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 · 130 lines · 49 tokens per session scan A e371287af5eb
applier is an agent published in the GitHub repository trebormc/drupal-ai-agents (10 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 49 tokens to every session and 815 once invoked, about $0.0002 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.