agentmods.dev

testing-from-prds

testing-from-prds is a skill for Claude Code from ihistand/claude-plugins. It costs 92 tokens per session (5,627 once invoked), scanned A, original, no licence file.

A workflow for writing or running software tests from a product requirements document (PRD) without reading the code. A PRD is a plain-language description of required product behaviour.

In plain words
What is it for?
It supports dry runs, tests for newly added or changed requirements, and characterization test suites for existing areas.
Why use it?
It keeps tests tied to stated requirements instead of accidentally copying the current implementation.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the prd-toolkit plugin — 9 skills, 10 commands, 2 agents, 1 hook shipped together

not rated 2repo changed today A scan 92 tokens no licence

Good fit It supports dry runs, tests for newly added or changed requirements, and characterization test suites for existing areas.

Compare 6 skills from other repositories ↓
View source ↗ ihistand/claude-plugins
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add ihistand/claude-plugins
Claude Code
/plugin install prd-toolkit

Made for: Claude Code.

Or install prd-toolkit, the plugin that ships this one along with the rest of its 9 skills, 10 commands, 2 agents, 1 hook.

Wrote 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.

agentmods badge for testing-from-prds

README.md
[![agentmods](https://agentmods.dev/badge/skills/ihistand/claude-plugins/testing-from-prds/github.svg)](https://agentmods.dev/skills/ihistand/claude-plugins/testing-from-prds)
Your own site
<a href="https://agentmods.dev/skills/ihistand/claude-plugins/testing-from-prds"><img src="https://agentmods.dev/badge/skills/ihistand/claude-plugins/testing-from-prds/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for testing-from-prds

Your own site · 80×15
<a href="https://agentmods.dev/skills/ihistand/claude-plugins/testing-from-prds"><img src="https://agentmods.dev/badge/skills/ihistand/claude-plugins/testing-from-prds.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 92 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,627 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin unknown No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00092 $0.05627
Opus 5.5 $0.00037 $0.02251
Sonnet 5.5 $0.00018 $0.01125
Haiku 4.5 $0.00009 $0.00563

Measured today against content hash 7ed653fb1d79, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

testing-from-prds scanned grade A with 1 finding 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 today.

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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

r = subprocess.run(["uv", "run", "--script", ".prd-toolkit/prd_judge.py",
prd-toolkit/skills/testing-from-prds/SKILL.md · 297 lines

The source is not reproduced here

No licence file

A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.

Read it on GitHub

Files

What ships with it

1 file 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.

Changes

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.

  1. today Changed · +13 lines 7ed653fb1d79
  2. 2d ago Changed · +10 lines 98af80e89843
  3. 5d ago Changed · +54 lines · +30 tokens per session 663b680f56dc
  4. 6d ago Changed · +17 lines 0812cbee33de
  5. 7d ago Changed · +12 lines 7b1b5ebfed7d
  6. 8d ago Changed 68c22f150aa6
  7. 9d ago First seen · 191 lines · 62 tokens per session scan A 6489862a1681

Subscribe to this mod's changes

testing-from-prds is a skill published in the GitHub repository ihistand/claude-plugins (2 stars, last pushed today), with no licence file. It adds 92 tokens to every session and 5,627 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-31.

PlanningTDDTesting
Related

testing-from-prds compared with skills from other repositories

testing-from-prds next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
testing-from-prdsihistand/claude-pluginsSkill2todaynoneA92Claude Code
engram-testing-coverageGentleman-Programming/engramSkill7.9k2d agoMITA25Claude Code, Codex
principle-test-behavior-not-implementationmichael-denyer/pstack-claudeSkill4.1kyesterdayMITA50Claude Code
tddcodewithmukesh/dotnet-claude-kitSkill8085d agoMITA81Claude Code
nw-ddd-eventsourcingnWave-ai/nWaveSkill6332d agoMITA38Claude Code
nw-fp-clojurenWave-ai/nWaveSkill6332d agoMITA25Claude Code
nw-leanux-methodologynWave-ai/nWaveSkill6332d agoMITA37Claude Code