A test-case tool for coding-agent plugins. It runs a plugin in a simulated environment with mocked platform tools, then grades the conversation and compares results with a saved baseline.

Use it to add or edit evaluation cases, graders, and tool mocks; run the suite; compare results; and update the expected baseline.

It helps detect regressions, meaning a change that makes an existing behaviour worse, when prompts, tools, skills, or graders are edited.

How Cognigy/cognigy-plugin configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to Cognigy/cognigy-plugin. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/Cognigy/cognigy-plugin/main/.claude/skills/add-eval/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/Cognigy/cognigy-plugin

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/cognigy/cognigy-plugin/add-eval/github.svg)](https://agentmods.dev/skills/cognigy/cognigy-plugin/add-eval)

Your own site

<a href="https://agentmods.dev/skills/cognigy/cognigy-plugin/add-eval"><img src="https://agentmods.dev/badge/skills/cognigy/cognigy-plugin/add-eval/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/cognigy/cognigy-plugin/add-eval"><img src="https://agentmods.dev/badge/skills/cognigy/cognigy-plugin/add-eval.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 75 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,552 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original 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.

Model	Per session	Once invoked
Fable 5.1	$0.00075	$0.01552
Opus 5.5	$0.00030	$0.00621
Sonnet 5.5	$0.00015	$0.00310
Haiku 4.5	$0.00007	$0.00155

Measured 18d ago against content hash 19bf1174f97f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

add-eval 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 18d 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.

.claude/skills/add-eval/SKILL.md · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Evals run the plugin in a sandboxed claude -p child against a mocked platform server and grade the transcript. Reference: https://code.claude.com/docs/en/plugin-evals.md (claude plugin eval --help matches it).

Layout

plugin/evals/
  <group>/<case>/prompt.md        frontmatter (tags, max_turns, allowed_tools) + the prompt, sent verbatim
  <group>/<case>/graders/<name>.md  one grader per file
  <group>/<case>/mocks/platform/<tool>.md  per-case override of one tool
  mocks/platform/_server.md       judge model plays a fixed demo tenant for every tool
  mocks/platform/_tools.json      real descriptions/schemas — generated, never hand-edit
  baseline.json                   committed per-grader pass rates, see "Run and compare"
  results/                        gitignored run output

Groups today: skill-triggers/, tool-choice/. The demo tenant (Demo Project, Billing Bot, Phone Support, GPT-4o) is defined in _server.md; write prompts against it.

Write a case

Copy the closest existing case. The prompt is phrased like a user, never names the skill or tool, and contains everything needed — the run starts in an empty directory and cannot ask follow-ups. Add "I'm not around to answer questions, so pick sensible defaults and go ahead." unless asking IS the behaviour under test (tool-choice/backup-gate).
Give it one grader on the steps (tool_used / tool_order / trace regex) and, where there is a result to judge, one on the outcome (regex on last_message, or a short llm rubric written as PASS/FAIL conditions).
Set max_turns generously (25–30 for build flows); hitting it is a run error. Judge-played mocks get 4 × max_turns calls.
Smoke it: npm run evals -- --case <name> --runs 1 --keep-temp, then read <kept>/out/trace.jsonl and out/mock-calls.jsonl to confirm the run took the path you meant — a pass can be for the wrong reason.
Run it at 3 runs and re-baseline (below).

MCP tools are named mcp__plugin_cognigy_platform__<tool>; plugin skills are invoked as cognigy:<skill>.

Read the full file on GitHub · 68 lines

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.

18d ago First seen · 68 lines · 75 tokens per session scan A 19bf1174f97f

Subscribe to this mod's changes

add-eval is a skill published in the GitHub repository Cognigy/cognigy-plugin (18 stars, last pushed yesterday), licensed MIT. It adds 75 tokens to every session and 1,552 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-10-20.

Testing

add-eval next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
add-evalCognigy/cognigy-plugin	Skill	18	yesterday	MIT	A	75	Claude Code
imagegenopenai/codex	Skill	133k	yesterday	Apache-2.0	A	113	Codex
playwright-climicrosoft/playwright	Skill	99k	yesterday	Apache-2.0	A	19	Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	4d ago	MIT	A	200	Claude Code, Codex
systematic-debuggingobra/superpowers	Skill	313k	3d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	95	Claude Code
next-partial-prefetching-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	103	Claude Code

cognigy-plugin: Skill for Claude Code