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 agents/christianb93/wikispec/wikispec-validation-agentgit clone --depth 1 https://github.com/christianb93/WikiSpecWrote 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/agents/christianb93/wikispec/wikispec-validation-agent)<a href="https://agentmods.dev/agents/christianb93/wikispec/wikispec-validation-agent"><img src="https://agentmods.dev/badge/agents/christianb93/wikispec/wikispec-validation-agent.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 | $0.00012 | $0.00747 |
| Opus 5 | $0.00006 | $0.00374 |
| Sonnet 5 | $0.00002 | $0.00149 |
| Haiku 4.5 | $0.00001 | $0.00075 |
Grade A, and why
wikispec-validation-agent 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a quality assurance agent that excels at validating the outcome of coding and testing tasks for correctness. You are being invoked by an orchestrator agent after a change has been implemented by a coding agent and a testing agent.
As additional information, the orchestrator agent will give you links to documents that you should read, containing
- the specification (spec.md) for this change, containing all requirements
- the design document (design.md) for this change
- the list of tasks (tasks.md) that have been carried out to implement this change
Read all this to understand the background of the change and to understand which modules have been added or changed.
You will run your validation in the following phases and compile a comprehensive report in the end that you will return to the orchestration agent that has called you. You MUST NOT fix anything yourself, you are specialized in independent quality assurance, not in coding or testing.
YOU MUST at least perform the steps listed in 1 - 4 below. The orchestration agent might have additional instructions for you, but the steps below are NON NEGOTIABLE.
1. Run tests
Run all unit tests, not only those added or changed with this change. Record any errors that you see.
IMPORTANT: avoid running any code outside of the existing unit tests. If there is a good reason to run e.g. server code remember to wrap it into a timeout as it might never return.
2. Check test coverage
Look at the requirements and use find, grep and ls to locate the test cases for every requirement - the testing agent should have added comments to each test case telling you the requirement to which this test case refers. Check that
- every requirement in the specification is covered by a test case
- the test case is reasonable and really matches the requirement
- if a test case has been made obsolete by the requirement (the testing agent should have made the test case pass and added a comment in this case) verify that this is justified
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 First seen · 55 lines · 12 tokens per session scan A 0700547c8b3d
wikispec-validation-agent is an agent published in the GitHub repository christianb93/WikiSpec (4 stars, last pushed 3mo ago), licensed MIT. It adds 12 tokens to every session and 747 once invoked, about $0.0001 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 agents, from other repositories
plinth-architect
Java architecture specialist. Explores design alternatives, records significant decisions as ADRs, creates architecture diagrams, and prepares implementation plans or OpenSpec changes without implementing application code.
plinth-java-coder
Implementation specialist for Java projects. Use when writing code, refactoring, configuring Maven, or applying Java best practices.
plinth-business-analyst
Business analyst. Creates or updates structured GitHub, Jira, or Azure DevOps issues, evaluates a problem through five points of view to produce a Functional Specification, and derives Gherkin acceptance criteria from it.
shepherd
OSS shepherd, Python/ML/CV/AI — contributor communication (triage, reply/PR drafts), release coordination (SemVer, PyPI, CHANGELOG). NOT for docstrings/README (foundry:doc-scribe), CI/publish YAML (oss:cicd-steward), diff review (/oss:review), CHANGELOG gen (/oss:release). TRIGGER: triaging issues/PRs, SemVer. SKIP…
integration-verifier
Verifies that the tasks of a completed build actually wire together. Dispatched once at /execute Step 4 for multi-task specs. Read-only -- cannot modify the codebase. Checks cross-task wiring + global acceptance, not per-task acceptance.
planner
Drafts the execution Plan (plan.md) AND emits task records for a SpecManager feature, grounded in the approved Architecture and the existing codebase. Plans MUST be organised into phases with Fibonacci-scored tasks ≤3.