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 skills/aveproject/ave/tddnpx skills add aveproject/ave --skill tddgit clone --depth 1 https://github.com/aveproject/aveWhat 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 | $0.00249 |
| Opus 5 | $0.00000 | $0.00125 |
| Sonnet 5 | $0.00000 | $0.00050 |
| Haiku 4.5 | $0.00000 | $0.00025 |
Grade A, and why
tdd 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
tdd — ave
For this repo, TDD means: fixtures first, then rule, then record validation.
Loop for a new rule
- Write the positive fixture (the malicious file)
- Write the negative fixture (the benign lookalike)
- Write a test asserting the rule fires on positive, not on negative → FAIL
- Write the rule → test PASSES
- Write the AVE record JSON
- python scripts/validate_records.py → record valid
- pytest tests/ -x -q → full suite green
What/Why/How on validation functions
# What: returns True if every record in records/ validates against the schema
# Why: one malformed record breaks every scanner that loads the record set
# How: loads each JSON, runs jsonschema.validate, collects all errors
def all_records_valid() -> tuple[bool, list[str]]:
...
The negative fixture rule
Every rule needs a negative fixture that looks SIMILAR to the positive but is benign. A rule with only a positive fixture is a false-positive waiting to happen. Test that the rule does NOT fire on the negative.
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 · 30 lines · 0 tokens per session scan A 55ae3ed36749
tdd is a skill published in the GitHub repository aveproject/ave (17 stars, last pushed 3d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 249 tokens. 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
skill-inspector
Review AI agent skills before installation using NVIDIA SkillSpector and source-aware semantic review. Use when asked whether a skill or downloaded skill folder is safe, trustworthy, installable, over-permissioned, or malicious.
chef-assistant
Use when cooking or planning meals, troubleshooting recipes, learning culinary techniques.
creative-writing-coach
Helps users with creative writing and storytelling.
personal-assistant
A personalized assistant that remembers your preferences.
onboarding-guide
Guides new users through a friendly onboarding experience.
terraform-deployer
Deploy infrastructure using Terraform.