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/codeblockz/langchain-community-plugin/test-skillsgit clone --depth 1 https://github.com/Codeblockz/langchain-community-pluginWhat 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 | $0.00020 | $0.00359 |
| Opus 5 | $0.00010 | $0.00179 |
| Sonnet 5 | $0.00004 | $0.00072 |
| Haiku 4.5 | $0.00002 | $0.00036 |
Grade A, and why
test-skills 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.
What it actually says
Test Skills Command
Validate skill content for correctness.
What It Checks
- Python syntax - Are code blocks valid Python?
- Anti-patterns - Using Pydantic for state? Missing checkpointer?
- Deprecated APIs - Using old import paths?
- Import paths - Do imports exist in current LangChain?
- Structure - Has Critical Rules and Common Gotchas sections?
Workflow
Step 1: Ask what to validate
What would you like to validate?
1. All skills
2. langgraph
3. langchain-rag
4. langchain-chains
Step 2: Run validation
cd ${CLAUDE_PLUGIN_ROOT}/..
python -m testing.cli validate --skill <selected>
# or
python -m testing.cli validate --all
Step 3: Show results
Report any errors or warnings found, with suggestions for fixes.
Quick Check
For a fast pass/fail overview:
python -m testing.cli quick
Example Output
============================================================
Skill: langgraph
============================================================
Code blocks checked: 8
Status: PASSED (2 warnings)
Issues:
[WARN] [block 3, line 5] Code contains TODO/FIXME placeholder
Rule: code/placeholder-todo
[WARN] Skill should have a 'Common Gotchas' section
Rule: structure/missing-gotchas
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 · 70 lines · 20 tokens per session scan A a9c7aa1b72ad
test-skills is a command published in the GitHub repository Codeblockz/langchain-community-plugin (3 stars, last pushed 7mo ago), licensed Apache-2.0. It adds 20 tokens to every session and 359 once invoked, about $0.0001 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 commands, from other repositories
date
询问当天的日期,输出的格式为 yyyy-MM-dd 星期几.
add-eval
Create a new evaluator for assessing agent performance.
human-in-the-loop
Add human approval or intervention points to your workflow.
run-evals
Execute the evaluation suite against the LangGraph agent.
add-subgraph
Create a modular subgraph that can be composed into the main workflow.
debug-graph
Help debug issues with the LangGraph workflow.