validate

validate is a skill for Claude Code from HirogaKatageri/hirokata. It costs 117 tokens per session (2,370 once invoked), scanned A, original, MIT.

A read-only checker for a project's guild board, using defined expectations and database assertions to verify that its records and workflow rules still hold.

In plain words
What is it for?
Use it to validate the whole board or check the requirements and results of a named workflow.
Why use it?
It catches broken process rules or inconsistent board data without changing the real board.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: positional $N argument.

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 guild plugin — 20 skills, 15 agents shipped together

Good fit Use it to validate the whole board or check the requirements and results of a named workflow.

Compare 6 skills from other repositories ↓
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 HirogaKatageri/hirokata
Claude Code
/plugin install guild

Made for: Claude Code.

Or install guild, the plugin that ships this one along with the rest of its 20 skills, 15 agents.

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 validate

README.md
[![agentmods](https://agentmods.dev/badge/skills/hirogakatageri/hirokata/validate/github.svg)](https://agentmods.dev/skills/hirogakatageri/hirokata/validate)
Your own site
<a href="https://agentmods.dev/skills/hirogakatageri/hirokata/validate"><img src="https://agentmods.dev/badge/skills/hirogakatageri/hirokata/validate/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 validate

Your own site · 80×15
<a href="https://agentmods.dev/skills/hirogakatageri/hirokata/validate"><img src="https://agentmods.dev/badge/skills/hirogakatageri/hirokata/validate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 117 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,370 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00117 $0.02370
Opus 5.5 $0.00047 $0.00948
Sonnet 5.5 $0.00023 $0.00474
Haiku 4.5 $0.00012 $0.00237

Measured 1mo ago against content hash eeba49575667, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

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 1mo 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.

plugins/guild/skills/validate/SKILL.md · 179 lines

How it starts

The opening of the file, as written. The whole thing — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Validating the guild

There is no code left to unit-test. What can fail now is a member reading the schema and the process, understanding some of it, and doing something adjacent to what was needed.

docs/expectations.md is the specification that catches that, and because the data model is a database, every expectation in it is a SQL assertion with a stated expected result rather than prose to be interpreted. This skill runs them and reports what holds.

Read-only by default, and say so in the report. The only path that writes is --fixture, which is gated behind a confirmation and refuses a board holding real work.

The surface

invocation what runs
validate §3 — the eleven global invariants. They hold whatever just ran.
validate <process> §3, then that process's preconditions, postconditions and anti-expectations.
validate --fixture <name> Loads a fixture into a scratch database, then asserts against it. Writes.

<process> names a skill, and the section it maps to:

process section process section
new-requirement §4 the build flow release §9
brief §5 qa §10 the maintenance cycle
dashboard §6 shift §11 the unattended shift
check-in §7

§8 names no process: it is the anti-expectations for emptying a board, and the fresh-file procedure that stands in for one. Its assertion, nothing was deleted, is G11 and runs with every other global.

<name> is one of empty, planned, in-flight, review-ready, messy, maintenance — docs/expectations-fixtures.md.

The shape every assertion has

Zero rows when healthy, the offending rows when not, so a failure names its own cause. finding-open-past-gate-repairs|1|REQ-001 tells you the row, the requirement and the rule; a boolean FAIL tells you to go looking. Any output at all is a failure.

A handful state a count or a value instead — §4.b expects exactly the plan gate row, §4.c expects N+10 | 2N+11 | 2, P4.a expects version 8. The sentence above each block says which. Read it; do not assume the zero-rows shape.

Read the full file on GitHub · 179 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.

  1. 1mo ago Changed eeba49575667
  2. 1mo ago Changed f13c8f3a5595
  3. 1mo ago First seen · 179 lines · 117 tokens per session scan A 8804d1438193

Subscribe to this mod's changes

validate is a skill published in the GitHub repository HirogaKatageri/hirokata (6 stars, last pushed 9d ago), licensed MIT. It adds 117 tokens to every session and 2,370 once invoked, about $0.0005 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 2026-09-04.