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.
/plugin marketplace add juanmhidalgo/claude-plugins/plugin install github-issuesWrote 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/juanmhidalgo/claude-plugins/verify)<a href="https://agentmods.dev/skills/juanmhidalgo/claude-plugins/verify"><img src="https://agentmods.dev/badge/skills/juanmhidalgo/claude-plugins/verify/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/juanmhidalgo/claude-plugins/verify"><img src="https://agentmods.dev/badge/skills/juanmhidalgo/claude-plugins/verify.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00086 | $0.01288 |
| Opus 5.5 | $0.00034 | $0.00515 |
| Sonnet 5.5 | $0.00017 | $0.00258 |
| Haiku 4.5 | $0.00009 | $0.00129 |
Grade A, and why
verify 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 14d 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 — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context
- Repository: !
git remote get-url origin 2>/dev/null || echo "no remote" - Checkout path: !
git rev-parse --show-toplevel 2>/dev/null - HEAD: !
git log -1 --format='%h %cs' 2>/dev/null - Current branch: !
git branch --show-current
Arguments
$ARGUMENTS
- One or more issues: URLs, or
#N/Nfor this repo (gh repo view --json nameWithOwner). - Or
--label <label>with optional--limit N(default 10): open issues with that label, viagh issue list --repo {owner}/{repo} --label <label> --state open --limit N --json number,title.
Verification runs against the local checkout, so issues must belong to this repo. An issue from another repo → STOP and say which checkout to run it from.
If the current branch is not the default branch, say so: the ledger is only true for this HEAD.
Herdr pane
With --pane, run the verification in a Herdr pane in collect mode: follow
${CLAUDE_PLUGIN_ROOT}/references/herdr-pane.md. It falls back to the normal run outside
Herdr. Questions the run asks happen in the pane, and Herdr notifies the user.
--pane / --no-pane are flags: drop them before reading the arguments.
Resolve the list here first (step 1), so the pane receives issue numbers, not a
label query that could resolve differently by the time it runs.
- Command string:
/github-issues:verify <resolved issue numbers> --no-pane - Report:
<scratchpad dir>/verify-<first issue>.md - Present: the ledger and verdicts as the report has them. Anything the pane posted to GitHub was approved there; do not offer to post it again.
Workflow
1. Resolve the list
Resolve the arguments into issue numbers. With more than 10, show the list and ask before continuing — each issue costs one agent.
2. Verify in parallel
Spawn one github-issues:issue-verifier per issue, all in a single message. Do not pass a
name to the Agent tool. Each prompt is exactly:
ISSUE: {owner}/{repo}#{number}
REPO_PATH: {checkout path}
RULES: {base directory of this skill}/../work/references/verification.md
{base directory of this skill}/../work/references/work-types.md
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.
- 14d ago Changed · +15 lines 6ac515434ad7
- 27d ago First seen · 121 lines · 86 tokens per session scan A 5fb9d9170a18
verify is a skill published in the GitHub repository juanmhidalgo/claude-plugins (8 stars, last pushed 6d ago), licensed MIT. It adds 86 tokens to every session and 1,288 once invoked, about $0.0003 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 2026-09-24.
Other skills, from other repositories
issue
Use when starting a chain from a GitHub issue — turning an issue URL or number into a triaged, planned, dispatched, and reviewed pull request. Classifies the thread (bug → root-cause discipline, feature → plan chain, question → drafted reply), synthesizes a spec from the issue's own acceptance criteria, then runs the…
github-triage
Use when triaging GitHub issues or pull requests - categorizing, labeling, organizing open items, validating if issues are still relevant, and reviewing/merging PRs. Handles taxonomy discovery, label creation, bulk tagging, issue staleness checks, and full PR review + merge workflows.
finn-review
Review open PRs against their linked Linear issues and required GitHub checks, then post a three-group verdict with Finn-loop labels. Use when asked to run Finn-loop's reviewer or review its PR queue. Designed for /loop; never merges or pushes code.
next-issue
Work the next open item on the issue.
vllm-daily-pr-issue-tracker
Track daily PRs and Issues from vllm-project/vllm and vllm-project/vllm-ascend, filter by model (DeepSeek/Qwen/GLM/MiniMax/Kimi) and tech topics (PD disaggregation, MTP, quantization, graph mode, performance), analyze with LLM, and generate a Markdown report. Use when user wants vllm daily tracker, PR/Issue digest, or…
github-triage
Use when transitioning open GitHub issues through a 7-state label-based triage state machine (triage:new through triage:done) by reading issue bodies and evidence rather than waiting for maintainer triggers, and producing per-issue agent briefs and out-of-scope rationales.