What is issue-validate?

A procedure for completing validation-labelled issue tasks by running their checks and recording whether they passed or failed.

Use it to preflight a validation issue, run its checklist, record SUCCESS or FAILURE as a comment, and close it only after success.

It separates checking existing behavior from changing code and prevents results from being claimed without actually running the check.

issue-validate — Skill for Claude Code by vergil-project

Install

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.

Any agent

npx skills add vergil-project/vergil-claude-plugin --skill issue-validate

Clone the repo

git clone --depth 1 https://github.com/vergil-project/vergil-claude-plugin

Made for: Claude Code.

Or install vergil, the plugin that ships this one along with the rest of its 15 skills, 1 agent, 2 hooks.

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/vergil-project/vergil-claude-plugin/issue-validate.svg)](https://agentmods.dev/skills/vergil-project/vergil-claude-plugin/issue-validate)

Your own site

<a href="https://agentmods.dev/skills/vergil-project/vergil-claude-plugin/issue-validate"><img src="https://agentmods.dev/badge/skills/vergil-project/vergil-claude-plugin/issue-validate.svg" alt="Measured on agentmods" height="20"></a>

Per session 56 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,213 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	$0.00056	$0.01213
Opus 5	$0.00028	$0.00607
Sonnet 5	$0.00011	$0.00243
Haiku 4.5	$0.00006	$0.00121

Measured 7d ago against content hash 095e8dd1015a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

issue-validate 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 7d 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.

skills/issue-validate/SKILL.md · 110 lines

How it starts

The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Issue Validate

Run a validation task to completion and record the result. Validation is one operational task kind — it follows the shared operational-task lifecycle (preflight → preconditions gate → run → record Outcome: → close-on-success / hold-open-on-failure); below is the validation-specific detail. A validation task's acceptance is proven by running its checklist and recording SUCCESS/FAILURE as a comment; it has no code PR and closes only on SUCCESS.

This is the sibling of issue-implement, and deliberately different:

	`issue-implement`	`issue-validate` (this)
Goal	Write code, solve a problem	Run a recorded check, observe reality
Workspace	Worktree + branch + commits	None — touches no code
Terminal state	PR handoff (`vrg-submit-pr`)	SUCCESS/FAILURE comment + close
On failure	Fix in place, iterate	Record FAILURE, file fix task(s), leave open

If you were sent here for an issue that is not validation-labelled, stop — that is code-implementation; use issue-implement.

Never fabricate a result

If you cannot actually run a check, say so and stop — never fabricate or partially fake a result. Use whatever means are efficient to run it (sub-agents encouraged); oversight is front-loaded and at the hard gates, not in a live transcript (the Front-Loaded Judgment, Trusted Execution doctrine; see CLAUDE.md). If you hit a problem you cannot resolve, stop and ask.

Preflight

Confirm you are the USER agent: vrg-whoami --mode must print user.
Confirm the issue carries the validation label:
```
vrg-gh issue view <N> --json labels
```
If it does not, this is the wrong skill — hand it to issue-implement.
Read the issue body. It is a self-contained scaffold: preconditions, commands, acceptance criteria, and a results template.

Gate on the preconditions FIRST

Before running anything, work the issue's Preconditions self-check — whatever form it declares (a machine probe or a human-attested statement; the framework prescribes no mechanism). This includes confirming the target is reachable and that the dependency change is actually deployed (the issue's Blocked-by: deps should be closed/merged).

Read the full file on GitHub · 110 lines

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.

references/operational-task-lifecycle.md 2.5 KB

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.

7d ago First seen · 110 lines · 56 tokens per session scan A 095e8dd1015a

Subscribe to this mod's changes

issue-validate is a skill published in the GitHub repository vergil-project/vergil-claude-plugin (2 stars, last pushed 5d ago), licensed MIT. It adds 56 tokens to every session and 1,213 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.

Testing

research-engineer

An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.

davila7/claude-code-templates · 43 tokens

tika-eval-compare

Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".

apache/tika · 50 tokens

neuron-evaluation-engineer

Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…

neuron-core/neuron-ai · 77 tokens

issue-validate