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/graphistry/pygraphistry/test-amplificationnpx skills add graphistry/pygraphistry --skill test-amplificationgit clone --depth 1 https://github.com/graphistry/pygraphistryWhat 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 | $0.00056 | $0.02852 |
| Opus 5 | $0.00028 | $0.01426 |
| Sonnet 5 | $0.00011 | $0.00570 |
| Haiku 4.5 | $0.00006 | $0.00285 |
Grade A, and why
test-amplification 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 — 433 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Test Amplification Skill
When to Use
- A pygraphistry feature area is stable enough to use but still yields recurring bugs.
- You need to grow tests from evidence, not random additions.
- You want reusable patterns that apply beyond one subsystem (for example, beyond GFQL).
Goal
Turn historical and newly found bugs into:
- A reusable bug taxonomy.
- Prioritized concrete test tasks.
- Implemented tests (plus minimal fixes when needed).
- Clear validation evidence and checkpoint commits.
Required Inputs
- Current branch context.
- Target feature area(s).
- Existing test locations for those areas.
- Safety constraints (for example: pure vectorized path, pandas+cudf compatibility, remote protocol constraints).
Multi-Round Artifact Rules (Required)
This workflow is usually iterative. Keep artifacts cleanly separated by round, plus cumulative rollups.
Round IDs
- Use zero-padded round IDs:
round-001,round-002, ... - Keep a stable task root:
plans/<task>/
Round-Scoped Artifacts
Per round, write under:
plans/<task>/rounds/round-00N/
Recommended files:
user_testing_playbook.mdfeature-risk-analysis.mddiscovery-matrix.mdbug-retro-5whys.mdtaxonomy-and-task-plan.mdexecution-report.mdmetrics.md
Cumulative Artifacts
Maintain cumulative rollups under:
plans/<task>/cumulative/
Recommended files:
feature-risk-analysis-cumulative.mdbug-retro-5whys-cumulative.mdtaxonomy-cumulative.mdround-metrics-ledger.mdcontinue-or-halt-log.md
Naming Conventions
- Prefer deterministic names inside round folders (no random suffixes).
- If date is needed, use ISO format:
YYYY-MM-DD. - Every round must update:
- one round-scoped
metrics.md - cumulative
round-metrics-ledger.md - cumulative
continue-or-halt-log.md
- one round-scoped
Parallel Subagent Protocol (Recommended When Available)
If parallel subagents are available (for example, Claude workers), use them with fixed artifact locations so work is crash-resumable.
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 · 433 lines · 56 tokens per session scan A acde435bf5b9
test-amplification is a skill published in the GitHub repository graphistry/pygraphistry (2,551 stars, last pushed today), licensed BSD-3-Clause. It adds 56 tokens to every session and 2,852 once invoked, about $0.0003 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
chart-creator
数据可视化图表生成（折线图、柱状图、饼图、散点图、雷达图、漏斗图）.
accelerated-computing-cudf
Official NVIDIA-authored guidance for NVIDIA cuDF GPU DataFrames, pandas acceleration, dask-cuDF, ETL, joins, groupby, CSV/Parquet I/O, nullable semantics, and multi-GPU DataFrame workloads.
graphify
Use for any question about a codebase, its architecture, file relationships, or project content — especially when graphify-out/ exists. Turns any input (code, docs, papers, images, videos) into a persistent knowledge graph with god nodes, community detection, and query/path/explain tools. Use when you need to…
graph-mutation-plan
Cookbook for composing an applygraphmutations plan — stable entitykey patterns, the canonical label/edge vocabulary, evidence/invalidation/confidence discipline, and a worked example. Load this when building a non-trivial mutation plan.
infographic-creator
基于给定文字内容创建精美信息图。当用户请求创建信息图时使用。.
code-to-diagram
Analyze codebases and automatically generate architecture diagrams, flowcharts, and org charts. Uses AST parsing to map import dependencies for Python, JS/TS, Go, and Java, outputting Mermaid or SVG files. Triggered when users ask to visualize code architecture, understand dependencies, draw a flowchart, or create a…