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 alunduil/alunduil-chezmoi --skill issue-linksgit clone --depth 1 https://github.com/alunduil/alunduil-chezmoiWrote 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/alunduil/alunduil-chezmoi/issue-links)<a href="https://agentmods.dev/skills/alunduil/alunduil-chezmoi/issue-links"><img src="https://agentmods.dev/badge/skills/alunduil/alunduil-chezmoi/issue-links/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/alunduil/alunduil-chezmoi/issue-links"><img src="https://agentmods.dev/badge/skills/alunduil/alunduil-chezmoi/issue-links.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 | $0.00067 | $0.01118 |
| Opus 5.5 | $0.00027 | $0.00447 |
| Sonnet 5.5 | $0.00013 | $0.00224 |
| Haiku 4.5 | $0.00007 | $0.00112 |
Grade A, and why
issue-links 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 1mo 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Issue links
Pick the strongest accurate relationship — but no stronger.
Decision tree
- Closes / Fixes / Resolves #N in PR body — auto-closes on merge. Default when a PR ends an issue.
- blocked-by / blocks — A can't proceed or ship until B lands. Both are peer-sized; B is not a piece of A. Surfaces in the dependency graph and gates closing.
- parent / sub-issue — A is decomposition of parent B's work. Sub wouldn't exist on its own; parent isn't done until subs are. Subs roll up into parent's progress.
- plain
#Nmention — context only, no causal edge. Discussion, prior art, "see also". Default when nothing stronger fits.
The trap: reaching for parent/sub-issue when blocked-by is what's meant, because sub-issues were the only hierarchy GitHub had for years. Size test — peer-sized → blocked-by; smaller-than-parent → sub-issue.
How to apply each
Closes / Fixes / Resolves
In the PR body or commit message:
Closes #123
Same-repo number, or owner/repo#123 cross-repo. Recognized verbs:
close, fix, resolve (any tense).
blocked-by (GraphQL only — no gh issue flag, no REST)
Two round-trips minimum: GraphQL executes one operation per request
and Mutation doesn't expose repository, so query and mutation
can't share a document. The lookup is aliased so both IDs return in
one call (one rate-limit point), then the mutation runs.
read A_ID B_ID <<<"$(gh api graphql \
-F owner=OWNER -F repo=REPO -F a=<A> -F b=<B> \
-f query='
query($owner: String!, $repo: String!, $a: Int!, $b: Int!) {
repository(owner: $owner, name: $repo) {
a: issue(number: $a) { id }
b: issue(number: $b) { id }
}
}' --jq '.data.repository | "\(.a.id) \(.b.id)"')"
gh api graphql -f a="$A_ID" -f b="$B_ID" -f query='
mutation($a: ID!, $b: ID!) {
addBlockedBy(input: { issueId: $a, blockingIssueId: $b }) {
issue { number }
blockingIssue { number }
}
}'
Cross-repo: lift each alias above repository so each issue gets
its own repo selection in the same query:
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.
- 1mo ago First seen · 113 lines · 67 tokens per session scan A 43bad3c2e8f8
issue-links is a skill published in the GitHub repository alunduil/alunduil-chezmoi (2 stars, last pushed today), licensed 0BSD. It adds 67 tokens to every session and 1,118 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.
Other skills, from other repositories
repository-history
Explain why code exists: Git blame, renames, reverts, and linked PRs.
github-repository
Set GitHub repo description, topics, merge policy, and security settings.
github-pull-request
Open, update, verify, and merge GitHub pull requests.
advanced-jj
Reference for deeper Jujutsu (jj) topics beyond the everyday describe/advance workflow covered in the active agent instructions. Load when working with conflicts, the operation log, bookmarks, revsets, fork/PR workflows, colocated Git repos, multi-remote setups, divergent changes, or jj config. Also the place to look…
checkout
Start work on a new issue or feature by creating a jj change on the up-to-date default branch with an optional named bookmark.
work-on
Ship a GitHub issue end to end by assessing complexity and composing the available research, planning, implementation, review, commit, and pull-request workflows.