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/avibebuilder/claude-prime/testnpx skills add avibebuilder/claude-prime --skill testgit clone --depth 1 https://github.com/avibebuilder/claude-primeWhat 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 | $0.00190 | $0.01478 |
| Opus 5 | $0.00095 | $0.00739 |
| Sonnet 5 | $0.00038 | $0.00296 |
| Haiku 4.5 | $0.00019 | $0.00148 |
Grade A, and why
test 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 3d 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 — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Route fast
| Situation | Steps |
|---|---|
run tests or a specific test path |
3 → 5 → 6 |
| The verification claim is already clear from the request or recent context | 4 → 5 → 6 |
| Behavioral claim but no tests exist | 1 → 4 manual path → 5 → 6 |
| Vague claim or broad change | Full flow |
Skip steps whose answers are already known from the conversation.
Flow
1. Define the claim
Figure out what must be true before running anything.
Possible sources:
- explicit argument
- stated request or acceptance criteria
- recent conversation
- recent diff or git status as fallback
Good claim: expired tokens return 401.
Bad claim: the app works.
If the claim is mushy, sharpen it before you touch the tools. Weak claims create noisy verification.
2. Scope only when needed
Skip if the claim is already scoped.
Use the change set to identify:
- deliverables — what must hold true
- coverage — what existing tests or manual checks could prove each deliverable
- blast radius — what nearby behavior could regress
For shared code, config, auth, schema, or similar cross-cutting changes, read references/regression-strategy.md before deciding how wide to test.
3. Find the project's real test entrypoints
Check in this order:
CLAUDE.mdpackage.json,Makefile,justfile,Taskfile- CI config
- test framework config
- existing test layout
Prefer project-defined commands over raw framework commands.
4. Choose the proof lane
Match the claim to the execution lane.
| Claim type | Lane |
|---|---|
| logic, transforms, business rules | direct tests |
| API behavior or contracts | backend verification |
| UI behavior or rendering | frontend verification |
| visual UI criteria | frontend visual verification |
| DB persistence | backend verification |
| CLI behavior | direct command verification |
| type or schema correctness | direct static verification |
| compile/build correctness | direct static/build verification |
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 3d ago First seen · 161 lines · 190 tokens per session scan A 0e463148d57c
test is a skill published in the GitHub repository avibebuilder/claude-prime (119 stars, last pushed 3mo ago), licensed MIT. It adds 190 tokens to every session and 1,478 once invoked, about $0.0010 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 2026-08-30.
Other skills, from other repositories
etsy-category-listing
Etsy category page scraper: given an Etsy category URL (e.g. https://www.etsy.com/c/jewelry) and optional page number, returns paginated product listings with listingId, shopId, title, url, image, salePrice, originalPrice, currency, rating, reviewCount, shopName, isAd, freeShipping, badge from category and subcategory…
agent-memory
../../../engineering/agent-memory/skills/agent-memory/SKILL.md.
agile-product-owner
../../../product-team/agile-product-owner/skills/agile-product-owner/SKILL.md.
amazon-reviews-api-skill
This skill helps users automatically extract Amazon product reviews via the Amazon Reviews API. Agent should proactively apply this skill when users express needs like getting reviews for Amazon product with ASIN B07TS6R1SF, analyzing customer feedback for a specific Amazon item, getting ratings and comments for a…
amazon-competitor-analyzer
Scrapes Amazon product data from ASINs using browseract.com automation API and performs surgical competitive analysis. Compares specifications, pricing, review quality, and visual strategies to identify competitor moats and vulnerabilities.
audit-reproducibility
Enforce the replication-protocol.md rule by cross-checking numeric claims in a manuscript against the actual R / Stata / Python outputs. Report PASS/FAIL per claim against tolerance thresholds. Use before submission and before releasing a replication package.