Borrowing it
Nothing to install: this file belongs to briancl2/CustomerNewsletter. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/briancl2/CustomerNewsletter/main/.github/skills/testing-prompt-changes/SKILL.mdgit clone --depth 1 https://github.com/briancl2/CustomerNewsletterWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/briancl2/customernewsletter/testing-prompt-changes)<a href="https://agentmods.dev/skills/briancl2/customernewsletter/testing-prompt-changes"><img src="https://agentmods.dev/badge/skills/briancl2/customernewsletter/testing-prompt-changes.svg" alt="Measured on agentmods" height="20"></a>What 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 5.1 | $0.00060 | $0.01634 |
| Opus 5 | $0.00030 | $0.00817 |
| Sonnet 5 | $0.00012 | $0.00327 |
| Haiku 4.5 | $0.00006 | $0.00163 |
Grade A, and why
testing-prompt-changes 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 6d 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 — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.
HIGR Prompt Testing
Test prompt and skill changes systematically with Hypothesis-Implement-Grade-Rework cycles. Every modification requires testable predictions and evidence-based grading against benchmark data.
Quick Start
- Write testable hypotheses before editing any prompt or skill
- Implement the change (delete superseded content)
- Run against benchmark inputs, compare to known-good output
- Grade each hypothesis: Good / Bad / Ugly
- Rework if needed; record results in
workspace/higr_log.md
When to Use
- Modifying phase prompts (
.github/prompts/phase_*.prompt.md) - Updating skill SKILL.md or references/
- Changing agent definition (
.github/agents/customer_newsletter.agent.md) - Changing copilot-instructions.md
- Any change that affects newsletter output quality
HIGR Cycle
flowchart LR
H[Hypothesis] --> I[Implement]
I --> G[Grade]
G --> R{Rework?}
R -->|Bad/Ugly| H
R -->|Good| D[Done]
Step 1: Hypothesis (Pre-Implementation)
Before editing any prompt or skill, write testable predictions:
| Hypothesis ID | Change | Expected Effect | Testable Criteria |
|---|---|---|---|
| H1 | [specific change] | [expected output difference] | [how to verify] |
Hypothesis Requirements:
- Specific — Not "newsletter will be better"
- Observable — Can see the difference in output
- Falsifiable — Possible to determine if wrong
Example Good Hypotheses:
| ID | Change | Expected Effect | Criteria |
|---|---|---|---|
| H1 | Add SOURCES.yaml reading to url-manifest | URL count increases, covers all kb/ sources | URL count within 20% of benchmark, 0 false URLs |
| H2 | Extract selection criteria to skill reference | Curation quality matches Dec 2025 benchmark | ≥70% item overlap with benchmark curated sections |
| H3 | Add IDE parity grouping to content-format-spec | IDE updates grouped correctly | VS Code/Visual Studio/JetBrains in single section |
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.
- 6d ago First seen · 173 lines · 60 tokens per session scan A 1211305eec34
testing-prompt-changes is a skill published in the GitHub repository briancl2/CustomerNewsletter (11 stars, last pushed 2mo ago), licensed MIT. It adds 60 tokens to every session and 1,634 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
deepeval
Use when discussing or working with DeepEval (the python AI evaluation framework).
prompt-enhancer
Transform poor or overly simple prompts with expert-level framing. Use when the user explicitly asks to improve, refine, or rewrite a prompt, or wants help framing a request for another AI system. Do NOT use for authoring, reviewing, or migrating system prompts or skills targeting a specific Claude model…
llm-prompting-guide
Prompt format rules for generative video and music models. Use when writing or reviewing a prompt for MiniMax H3 (text/image/reference-to-video with native audio) or MiniMax Music 3 (song generation from caption plus lyrics), in ComfyUI or elsewhere. Do NOT use for chat-assistant prompts, or for generative models not…
hatch3r-ai-feature
Eval-driven development workflow for shipping AI features — write eval before prompt, measure, iterate, ship with caching + cost telemetry + model fallback + hallucination SLI.
promptbeat-run-quick-eval
Use when a user has a Promptbeat config or generated promptfoo config and wants to validate, generate a few cases, run a first small evaluation, inspect artifacts, or create a report.
prompt-evaluation-runner
Use when evaluating prompts, LLM outputs, red-team suites, or model behavior with local eval configs and safe provider/cost controls.