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 agentmods add skills/tonydzi/second-brain-starter-kit/issue-matchnpx skills add tonydzi/second-brain-starter-kit --skill issue-matchgit clone --depth 1 https://github.com/tonydzi/second-brain-starter-kitWrote 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/tonydzi/second-brain-starter-kit/issue-match)<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="Measured on agentmods" 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 | $0.00100 | $0.01587 |
| Opus 5 | $0.00050 | $0.00794 |
| Sonnet 5 | $0.00020 | $0.00317 |
| Haiku 4.5 | $0.00010 | $0.00159 |
Grade A, and why
issue-match scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/issue-match — knock here, or walk past?
🧒 End the report to a non-technical owner with an "In plain words" block ([[eli5-always]]).
The owner's rule from 2026-07-25 ([[cold-pr-into-silent-queue]]): a cold PR into a silent queue is not a contribution, it's noise. Measuring the queue is the first step, BEFORE writing any code. This skill turns that measurement into a button instead of hand-driving gh in every session.
Measured 07-25 on anthropics/claude-cookbooks: 220 open PRs, median age 47 days, 51% without a single comment, 67% of merges happened within a day of submission (which means the agreement existed BEFORE the PR). We had 6 open there, 5 cold, 0 merged. The only one a human reacted to was the one that came in through someone else's open issue.
How to run it
python "$USERPROFILE/.claude/scripts/issue_match.py" anthropics/claude-cookbooks --artifact "search agent, adversarial verify"
| Command | What it does |
|---|---|
<owner/repo> |
measure a single repo |
--artifact "kw1, kw2" |
the main parameter — the keywords of our artifact, used to find the door |
--all |
fan out across every repo in the config (~5s per repo; 14 repos ≈ 70s) |
--init |
build the config from OUR PR history (gh finds where we submitted) |
--live-days N |
an issue counts as live if it was updated within N days (default 30) |
--json |
machine-readable output |
--no-draft |
skip the entry draft |
Config: ~/.claude/issue_match.json. Exit codes: 0 measurement done · 2 bad arguments · 4 gh unavailable or all fetches failed.
How to read the output
- QUEUE — open PRs (the exact count, not truncated by a limit), median age (when sampled, this is a lower bound, the real one is higher), the share with no comments, the merge pattern. If "merged on the day of submission" is ≥60%, that is not "they merge fast", that is pre-agreement; a cold PR will not reproduce that rhythm. Look at one-time authors: if none of the merges came from a one-time author, the repo merges only its own people, and a healthy median promises an outsider nothing.
- US THERE — how many of our PRs are sitting and how many got no reaction. Many cold ones = warm those up first instead of spawning new ones.
- DOORS — live third-party issues matching the keywords. Our own issues are counted separately: your own door is not an invitation.
- VERDICT — 🟢 enter through an issue · 🟡 open our own issue and wait · 🔴 don't push · ⚪ not measured (the issue fetch failed, or the door may have fallen outside the sample) — do not make a decision on that data, run the measurement again. A silent fetch is not an answer.
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.
- 4d ago First seen · 74 lines · 100 tokens per session scan A 7ccb46a9724a
issue-match is a skill published in the GitHub repository tonydzi/second-brain-starter-kit (5 stars, last pushed 5d ago), licensed MIT. It adds 100 tokens to every session and 1,587 once invoked, about $0.0005 per session on Opus 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.
Other skills, from other repositories
wiki-ingest
Ingest supplied source material into an Obsidian vault with provenance and claim tracking: pasted text, files staged in the selected vault's inbox or .raw archive, or explicitly approved URLs. Use for a single source or bounded batch, not for saving an assistant answer. Triggers: ingest, ingest this file, ingest this…
autoresearch
Run a bounded, source-grounded research loop, draft a cited dossier, and optionally propose a separately reviewed canonical vault merge. Use when the user wants autonomous or deep research that may access the public web. Triggers: /autoresearch, autoresearch, research this topic, deep dive into, investigate, find…
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.
wiki-retrieve
Build and query a vault-local contextual BM25 retrieval index with optional multilingual Nomic cosine reranking; use for retrieve, hybrid retrieval, BM25, rerank, contextual retrieval, chunk search, vault search, semantic search, find relevant passages, or retrieval diagnostics. Derived caches stay under .vault-meta…
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…
defuddle
Plan and, with explicit network consent, use an optional external Defuddle cleaner to extract article-like HTTPS pages as Markdown. Use for defuddle, clean this URL, strip page clutter, readable Markdown from a web page, or preparing a web source for later wiki ingestion.