validate-issue

validate-issue is a skill for Claude Code from richkuo/rk-skills. It costs 48 tokens per session (5,377 once invoked), scanned A, original, MIT.

A verification process for checking whether a GitHub issue accurately describes the current code and proposes a valid change. It examines the issue's claims, related pull requests, and implementation scope before returning one decision.

In plain words
What is it for?
Use it with an issue number, URL, or repository reference, or let it select the newest open issue. It checks behavior, cause, evidence, proposed fix, scope, and complexity.
Why use it?
It removes guesswork from deciding whether an issue is real, correctly understood, and ready to implement. This helps avoid building on outdated descriptions or unsupported assumptions.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions CLAUDE.md; mentions subagents; mentions Codex.

Part of the rk-skills plugin — 39 skills, 1 command shipped together

Good fit Use it with an issue number, URL, or repository reference, or let it select the newest open issue. It checks behavior, cause, evidence, proposed fix, scope, and complexity.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/richkuo/rk-skills/validate-issue
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 richkuo/rk-skills --skill validate-issue
Clone the repo
git clone --depth 1 https://github.com/richkuo/rk-skills

Made for: Claude Code.

Or install rk-skills, the plugin that ships this one along with the rest of its 39 skills, 1 command.

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-issue

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/richkuo/rk-skills/validate-issue"><img src="https://agentmods.dev/badge/skills/richkuo/rk-skills/validate-issue.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,377 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00048 $0.05377
Opus 5.5 $0.00019 $0.02151
Sonnet 5.5 $0.00010 $0.01075
Haiku 4.5 $0.00005 $0.00538

Measured 5d ago against content hash b67c276e1657, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

validate-issue 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 5d 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/validate-issue/SKILL.md · 189 lines

How it starts

The opening of the file, as written. The whole thing — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.

validate-issue

Validate every current-behavior claim against code. Input: issue URL, #N, N, or owner/repo#N; else the issue named, validated, planned, or filed this session, else stop and ask. Never pick an issue from a list. { issue: <N>, targetBranch?: "<branch>" } (or prose "target branch ") names the merge target, which replaces the default branch in step 0.

0. Baseline branch

No worktree for validation or issue edits. REPO: the repo a URL or owner/repo#N names, else the checkout's origin; pass --repo "$REPO" to every gh call, linked PRs included. If origin is another repo, trace REPO in a temporary clone outside this checkout; never cite another repo's code. DEFAULT=$(gh repo view "$REPO" --json defaultBranchRef --jq .defaultBranchRef.name); a targetBranch is validated per work-on-issue step 1 ("Target"), replaces DEFAULT, and is named as the target in the verdict. No network (gh and remote checks fail): use the caller's baseline branch (target, else its resolved default), else git symbolic-ref --short refs/remotes/origin/HEAD minus origin/; accept it if git rev-parse --verify "origin/$DEFAULT" succeeds, naming each skipped network check as a verification limitation. A branch with no local origin ref still blocks. Run git fetch origin "$DEFAULT" (a failure keeps the last fetched ref: verification limitation), then pin BASE=$(git rev-parse "origin/$DEFAULT") once. Every read, search, and history check uses BASE: git show "$BASE":<path>, git grep -n <pattern> "$BASE" -- <paths>, git log "$BASE" -- <paths>. Caller-pinned evidence commits (such as the milestone pipeline's hard-dependency base refs): trace code that exists only at one against it and cite the SHA; one missing locally is a verification limitation, and claims about code only it holds stay Unverified. The verdict states git rev-parse --short "$BASE" as the baseline. Issue unreadable or no BASE: stop with Validation blocked (step 8).

Read the full file on GitHub · 189 lines

Files

What ships with it

4 files 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.

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. 5d ago Changed b67c276e1657
  2. 21d ago Changed · +32 lines · +14 tokens per session 4a84599a1453
  3. 22d ago Changed 17c5da1bdbd1
  4. 23d ago Changed · -3 lines 6cd9eb163354
  5. 24d ago Changed 8188752befe2
  6. 28d ago Changed · +6 lines 8513cebfbc92
  7. 29d ago Changed 08cabc528719
  8. 1mo ago Changed · +4 lines 74fa9b42cf28
  9. 1mo ago Changed · +1 lines 1858bd316a0d
  10. 1mo ago First seen · 149 lines · 34 tokens per session scan A 299a02643ec6

Subscribe to this mod's changes

validate-issue is a skill published in the GitHub repository richkuo/rk-skills (50 stars, last pushed yesterday), licensed MIT. It adds 48 tokens to every session and 5,377 once invoked, about $0.0002 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 2026-08-30.

Related

Other skills, from other repositories

criticism-self-criticism

A structured review method for examining completed work, criticism, and repeated mistakes. It focuses on specific evidence, causes, effects, and practical improvements.

HughYau/qiushi-skill · 197 tokens

refactor

Expert code refactoring based on Martin Fowler's catalog — improve maintainability without changing behavior. Covers code smells, composing methods, moving features, organizing data, simplifying conditionals, method calls, and generalization. Triggers on: refactor, 重构, clean up, improve code, code smell, extract…

smallnest/goal-workflow · 71 tokens

walkthrough

Generate a Phase-2 Walkthrough artifact (walkthrough.md) once implementation and verification are complete. Captures a Change Summary, Verification Steps (commands + unit tests + automated browser testing outcomes), Visual Proof (screenshots/recordings embedded directly in the file), and a Review Gate (final diff + PR…

smallnest/goal-workflow · 131 tokens

understand

Review and understand freshly AI-generated code. Scans the current repo's uncommitted/branch changes and builds a Claude-style light-themed two-column webpage — left is the project folder tree of changed files, right is the selected file's syntax-highlighted diff (additions/deletions clearly distinguished from…

smallnest/goal-workflow · 125 tokens

aif-recon

Scout a codebase fast with native search, optional Explore agents and user-permitted OpenCode probes.

ainative-build/skills · 25 tokens

cross-review

You MUST use this when an implementation plan or a finished implementation needs an independent review by other agent CLIs - by default the opposite CLI (Codex for work done in Claude Code, Claude Code for work done in Codex) together with Antigravity (Gemini) - whether the user asks for a cross-review or a second…

sentimony/skills · 123 tokens