Borrowing it
Nothing to install: this file belongs to fruggr/zendesk-mcp-server. 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/fruggr/zendesk-mcp-server/main/.claude/skills/functional-validation-plan/SKILL.mdgit clone --depth 1 https://github.com/fruggr/zendesk-mcp-serverWrote 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/fruggr/zendesk-mcp-server/functional-validation-plan)<a href="https://agentmods.dev/skills/fruggr/zendesk-mcp-server/functional-validation-plan"><img src="https://agentmods.dev/badge/skills/fruggr/zendesk-mcp-server/functional-validation-plan.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 | $0.00056 | $0.01874 |
| Opus 5 | $0.00028 | $0.00937 |
| Sonnet 5 | $0.00011 | $0.00375 |
| Haiku 4.5 | $0.00006 | $0.00187 |
Grade A, and why
functional-validation-plan 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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Functional validation plan — author protocol
A code change is not "done" when the unit tests pass. Someone who did not write the code must be able to exercise the feature end-to-end and confirm it behaves as claimed. This skill produces the brief that lets them do that.
When to apply
- Whenever you produce an implementation plan that changes MCP-runtime- observable behaviour: the plan must include a functional validation plan as a first-class section, not an afterthought.
- Whenever you land a feature or bugfix whose behaviour is observable at MCP-server runtime (auth flows, transports, tool surface, resources, prompts, persistence, timing).
Skip for changes with no MCP-runtime-observable behaviour: pure docs, comments,
formatting, and pure tooling / dev-tooling (build scripts, the
typecheck/lint/format setup, dev-only scripts, CI, release automation) — those
are covered by the standard gates (pnpm typecheck / pnpm check / pnpm test
- CI), not a third-party functional pass. Say so explicitly rather than silently omitting the plan.
Hard rules
- Independent validator. Write the plan FOR someone other than the implementer — another agent (e.g. the local executor) or a human. Don't assume it shares your conversation context: spell out the state to manipulate and how to observe results. Independence is about context, not identity: every agent here posts under the same human's GitHub account, so a report is not the author's just because it carries the author's login. Judge it on its evidence, and leave the "does this count" call to the repository owner — stating the role behind a run once is enough.
- Assume a fully ready environment — don't make the validator build it. The
validator's session is already on the PR branch, in a live checkout, with the
MCP server running and authenticated and its tools loaded as
mcp__<server>__*(--mode all). So the plan must NOT ask the validator to:- check out / fetch / clone / pull the branch (it's already on it — at most,
capture
git rev-parse HEADto name the SHA); - build, install, or start the server (
pnpm …, transport choices,pnpm mcp:live, otherscripts/); - locate or configure credentials, tokens, or the base URL (a valid token is already wired into the running server and reused by any sanctioned script).
- check out / fetch / clone / pull the branch (it's already on it — at most,
capture
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 Changed · +7 lines 06ca4b18a251
- 8d ago First seen · 124 lines · 56 tokens per session scan A dfcf7cd9f618
functional-validation-plan is a skill published in the GitHub repository fruggr/zendesk-mcp-server (5 stars, last pushed 2d ago), licensed MIT. It adds 56 tokens to every session and 1,874 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 2026-08-31.
Other skills, from other repositories
blazemeter-private-locations
Comprehensive guide for BlazeMeter Private Locations, including Radar Agent, installation (Docker, Kubernetes, Helm), configuration, management, and troubleshooting. Use when working with Private Locations for (1) Installing agents (Docker, Kubernetes, Helm Chart), (2) Configuring Radar Agent for API Monitoring, (3)…
blazemeter-functional-testing
Comprehensive guide for BlazeMeter Functional Testing, including GUI Functional Tests, API Tests (deprecated), Action Library, and debugging. Use when working with Functional Testing for (1) Creating GUI Functional Tests (YAML, Java IDE, Python IDE), (2) Managing Functional Tests (duplicate, delete, move, rename), (3)…
blazemeter-recorders
Comprehensive guide for BlazeMeter Recorders, including Chrome Extension and Proxy Recorder. Use when working with recorders for (1) Recording tests with Chrome Extension, (2) Creating and using Proxy Recorder, (3) Configuring browsers and devices for proxy recording, (4) Setting port ranges for proxy recorder, or any…
lastest
Lastest is a visual regression testing platform. It records browser tests, runs them via Playwright, diffs screenshots, and uses AI to classify changes. Available as an MCP server for AI agent integration.
field-test
Exercise tools, resources, and prompts against a live HTTP server via MCP JSON-RPC over curl. Starts the server, surfaces the catalog, runs real and adversarial inputs, and produces a tight report with concrete findings and numbered follow-up options. Use after adding or modifying definitions, or when the user asks to…
field-test
Exercise tools, resources, and prompts against a live HTTP server via MCP JSON-RPC over curl. Starts the server, surfaces the catalog, runs real and adversarial inputs, and produces a tight report with concrete findings and numbered follow-up options. Use after adding or modifying definitions, or when the user asks to…