A check for whether a software repository has an open issue that matches a proposed contribution. It also measures the repository’s open and recently closed pull requests, which are proposed code changes.

Use it to inspect a repository’s contribution queue, find a relevant open issue, and decide whether to contribute there or skip it.

It helps you decide whether a repository is likely to review and accept your work before you spend time writing it. A busy or inactive queue can show that a direct pull request may be ignored.

issue-match — Skill for Claude Code by tonydzi

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 tonydzi/second-brain-starter-kit --skill issue-match

Clone the repo

git clone --depth 1 https://github.com/tonydzi/second-brain-starter-kit

Made for: Claude Code.

Or install second-brain-skills, the plugin that ships this one along with the rest of its 248 skills, 1 plugin.

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/tonydzi/second-brain-starter-kit/issue-match/github.svg)](https://agentmods.dev/skills/tonydzi/second-brain-starter-kit/issue-match)

Your own site

<a href="https://agentmods.dev/skills/tonydzi/second-brain-starter-kit/issue-match"><img src="https://agentmods.dev/badge/skills/tonydzi/second-brain-starter-kit/issue-match/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/tonydzi/second-brain-starter-kit/issue-match"><img src="https://agentmods.dev/badge/skills/tonydzi/second-brain-starter-kit/issue-match.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 87 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 4,598 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	$0.00087	$0.04598
Opus 5.5	$0.00035	$0.01839
Sonnet 5.5	$0.00017	$0.00920
Haiku 4.5	$0.00009	$0.00460

Measured 7d ago against content hash f2ffbba615d7, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

issue-match 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-match/SKILL.md · 177 lines

How it starts

The opening of the file, as written. The whole thing — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/issue-match — стучаться сюда или мимо?

🧒 В конце отчёта Антону — блок «Простыми словами» ([[eli5-always]]).

Правило Антона от 25.07.2026 ([[cold-pr-into-silent-queue]]): холодный PR в глухую очередь = не вклад, а шум. Замер очереди — первый шаг, ДО написания кода. Этот скилл делает замер кнопкой вместо ручного дёрганья gh в каждой сессии.

Замерено 25.07 в anthropics/claude-cookbooks: 220 открытых PR, медиана возраста 47 дней, 51% без единого комментария, 67% мержей — в сутки после подачи (значит договорённость была ДО PR). Наших там 6 открытых, 5 холодных, смержено 0. Единственный, на который отреагировал человек, — тот, что вошёл через чужое открытое issue.

Как гонять

python "$USERPROFILE/.claude/scripts/issue_match.py" anthropics/claude-cookbooks --artifact "search agent, adversarial verify"

Команда	Что делает
`<owner/repo>`	замер одного репо
`--artifact "kw1, kw2"`	главный параметр — ключевые слова нашего артефакта, по ним ищется дверь
`--all`	веер по всем репо из конфига (~5 с на репо; 14 репо ≈ 70 с)
`--init`	собрать конфиг из НАШЕЙ истории PR (`gh` сам находит, куда мы подавали)
`--live-days N`	issue считается живым, если обновлялся за N дней (дефолт 30)
`--json`	машинный вывод
`--no-draft`	без черновика входа

Конфиг: ~/.claude/issue_match.json. Exit: 0 замер сделан · 2 кривые аргументы · 4 gh недоступен или все заборы упали.

Что читать в выводе

ОЧЕРЕДЬ — открытых PR (точный счёт, не обрезанный лимитом), медиана возраста (при выборке — это оценка снизу, настоящая выше), доля без комментариев, паттерн мержей. Если «в день подачи» ≥60% — это не «быстро мёржат», это преддоговорённость; холодный PR такой ритм не повторит. Смотри «разовых авторов»: если среди мержей нет ни одного разового, репо мержит только своих и здоровая медиана чужаку ничего не обещает.
МЫ ТАМ — сколько наших PR лежит и сколько из них без реакции. Много холодных = сперва греть их, а не плодить новые.
ДВЕРИ — живые чужие issue с совпадением по ключевым словам. Наши собственные issue считаются отдельно: своя дверь не приглашение.
ВЕРДИКТ — 🟢 входим через issue · 🟡 открываем своё issue и ждём · 🔴 не пушим · ⚪ не замерено (забор issue упал или дверь могла остаться за выборкой) — на таких данных решение не принимаем, гоним замер заново. Молчание забора — не ответ.
⭐ ПРАВО ВХОДА (08.10.2026) — 🟢 «входим через issue» НЕ означает, что PR примут: репо может требовать assignment до PR и авто-закрывать остальное (pydantic/pydantic-ai#8582 → PR #9835 закрыт ботом через минуту, 05.10). Перед стройкой прогони дверь через python3 ~/.claude/scripts/door_claimcheck.py; GATED = не строим, сперва просим assignment в треде. ⛔ Логику здесь не дублируем — у прибора одна голова.

Read the full file on GitHub · 177 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.

7d ago Changed · +104 lines f2ffbba615d7
11d ago Changed · -1 lines 3e1017546807
16d ago Changed · -24 lines · -30 tokens per session b6c54a2cfe7c
25d ago Changed · +22 lines · +30 tokens per session a1af7d70f3ea
1mo ago Changed · +2 lines · -13 tokens per session d50596ce734a
1mo ago First seen · 74 lines · 100 tokens per session scan A 7ccb46a9724a

Subscribe to this mod's changes

issue-match is a skill published in the GitHub repository tonydzi/second-brain-starter-kit (9 stars, last pushed today), licensed MIT. It adds 87 tokens to every session and 4,598 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 2026-08-31.

Claude Code Git and workflow Project management ai-agents knowledge-management obsidian personal-knowledge-management second-brain

gh-issue-submit

A skill for submitting GitHub issues with the `gh` command-line tool. It guides issue-template discovery, duplicate checking, source investigation, submission, and verification.

Linearl/reasonix_skill_repo · 71 tokens

ll-iteration-dev

A workflow for developing several tasks in parallel using separate Git worktrees, which are independent working directories for one repository.

Linearl/reasonix_skill_repo · 220 tokens

canvas

Create, inspect, and update Obsidian JSON Canvas boards with text, file, link, group, and edge nodes. Use for canvas status, canvas lists, visual maps, zones, spatial layouts, adding vault notes or media to a .canvas file, and requests such as create canvas, add to canvas, or put this on the canvas.

AgriciDaniel/claude-obsidian · 72 tokens

wiki

Initialize, adopt, and route work for a separate Obsidian knowledge vault through the portable claude-obsidian core. Use for vault setup, scaffolding, workspace selection, cross-project configuration, or choosing the correct wiki sub-skill. Triggers: /wiki, set up wiki, scaffold vault, create knowledge base, adopt…

AgriciDaniel/claude-obsidian · 84 tokens

obsidian-markdown

Explain, draft, or validate Obsidian Flavored Markdown syntax: properties, wikilinks, embeds, callouts, tags, comments, highlights, block references, math, and Mermaid. Use when the user explicitly requests Obsidian note formatting or syntax help, not for general Markdown or broad vault operations.

AgriciDaniel/claude-obsidian · 68 tokens

wiki-fold

Create a bounded, extractive, structurally idempotent rollup of recent Obsidian wiki log entries, with dry-run preview by default and one optional transaction apply. Use for manual log compression without modifying child pages. Triggers: fold the log, run a fold, run wiki-fold, log rollup, roll up log entries, commit…

AgriciDaniel/claude-obsidian · 76 tokens