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 skills add richkuo/rk-skills --skill validate-issuegit clone --depth 1 https://github.com/richkuo/rk-skillsWrote 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/richkuo/rk-skills/validate-issue)<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.
<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>- NVIDIA SkillSpector pass
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 | $0.00048 | $0.05377 |
| Opus 5.5 | $0.00019 | $0.02151 |
| Sonnet 5.5 | $0.00010 | $0.01075 |
| Haiku 4.5 | $0.00005 | $0.00538 |
Grade A, and why
validate-issue scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
validate-issue
Validate every current-behavior claim against code. Input: issue URL, #N, N, or owner/repo#N; else the issue named, validated, planned, or filed this session, else stop and ask. Never pick an issue from a list. { issue: <N>, targetBranch?: "<branch>" } (or prose "target branch ") names the merge target, which replaces the default branch in step 0.
0. Baseline branch
No worktree for validation or issue edits. REPO: the repo a URL or owner/repo#N names, else the checkout's origin; pass --repo "$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).
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.
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.
- 5d ago Changed b67c276e1657
- 21d ago Changed · +32 lines · +14 tokens per session 4a84599a1453
- 22d ago Changed 17c5da1bdbd1
- 23d ago Changed · -3 lines 6cd9eb163354
- 24d ago Changed 8188752befe2
- 28d ago Changed · +6 lines 8513cebfbc92
- 29d ago Changed 08cabc528719
- 1mo ago Changed · +4 lines 74fa9b42cf28
- 1mo ago Changed · +1 lines 1858bd316a0d
- 1mo ago First seen · 149 lines · 34 tokens per session scan A 299a02643ec6
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.
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.
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…
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…
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…
aif-recon
Scout a codebase fast with native search, optional Explore agents and user-permitted OpenCode probes.
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…