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/pekral/cursor-rules/autoresolve-oldest-github-issuenpx skills add pekral/cursor-rules --skill autoresolve-oldest-github-issuegit clone --depth 1 https://github.com/pekral/cursor-rulesWrote 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/pekral/cursor-rules/autoresolve-oldest-github-issue)<a href="https://agentmods.dev/skills/pekral/cursor-rules/autoresolve-oldest-github-issue"><img src="https://agentmods.dev/badge/skills/pekral/cursor-rules/autoresolve-oldest-github-issue.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 | $0.00103 | $0.01855 |
| Opus 5 | $0.00051 | $0.00928 |
| Sonnet 5 | $0.00021 | $0.00371 |
| Haiku 4.5 | $0.00010 | $0.00186 |
Grade A, and why
autoresolve-oldest-github-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 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Constraints
- Apply
@rules/git/general.mdc - Apply
@rules/reports/general.mdc - Operate on the current Git repository's GitHub remote only — refuse if the remote is not GitHub
- Process exactly one issue per invocation; never loop into a second issue
- Never bypass quality gates of the delegated skills (
resolve-issue,code-review-github,process-code-review,merge-github-pr) - Code review is a hard merge gate (
@rules/git/general.mdcMerging): never reach step 6 (merge) until steps 4–5 have run a code review on the PR's final diff and driven it to 0 Critical + 0 Moderate. A merge without a converged code review is forbidden — do not skip or reorder steps 4–5 to merge sooner. - Never force-merge: stop on merge conflict, failing CI, missing approvals, or unresolved Critical/Moderate CR findings
- Never alter the original issue body, labels, or assignees outside what the delegated skills already do. Exception:
resolve-issueapplies theResolve_by_AI:in-progressclaim label at the start of work and releases it on a pre-PR Blocked/abort — this is a sanctioned write owned by the delegated skill, not a constraint violation. - Do not expose sensitive/internal details in user-facing messages
Use when
- The user wants the oldest open GitHub issue auto-resolved end-to-end (resolve → review → process feedback → merge)
- A scheduled or batch workflow needs a single deterministic entry point that chains the four skills
Inputs
LABEL(optional) — GitHub label used to filter eligible issues. Default:Resolve_by_AI. Pass an empty string (LABEL="") to disable label filtering and pick the globally oldest open issue.
Execution
1. Preflight
- Confirm
gh auth statusreports an authenticated session; if not, stop and ask the user to authenticate. - Resolve the current Git remote origin and verify it points to GitHub. Stop with a clear message otherwise.
- Switch to the
mainbranch and pull the latest changes.
2. Select the oldest issue
- Resolve the current repository slug:
REPO=$(gh repo view --json nameWithOwner -q .nameWithOwner). - Query the single oldest open issue via
gh search issues, which — unlikegh issue list— supports explicit ascending order and therefore returns the globally oldest match regardless of total open-issue count:
TheCLAIM_LABEL="${CLAIM_LABEL:-Resolve_by_AI:in-progress}" QUERY="is:open is:issue repo:${REPO}${LABEL:+ label:\"$LABEL\"} -label:\"${CLAIM_LABEL}\"" gh search issues "$QUERY" --sort created --order asc --limit 1 \ --json number,url,title,createdAt,labels,assignees-label:negation excludes any issue already carrying theResolve_by_AI:in-progressclaim label, so two parallel autoresolve runs always select different issues.CLAIM_LABELdefaults toResolve_by_AI:in-progressand can be overridden to match a repository that uses a custom claim label. Do not substitutegh issue list --sort created --limit <N>: that command returns the newestNissues with no--orderswitch, so any client-side ascending sort picks the oldest of the newest, never the true oldest. - If the result is empty, stop with the message
No eligible open GitHub issues found (label=<LABEL>). - Record the selected issue's
numberandurl. This URL is the single argument passed to every downstream skill in the chain.
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 · 89 lines · 103 tokens per session scan A 009640cccf3b
autoresolve-oldest-github-issue is a skill published in the GitHub repository pekral/cursor-rules (6 stars, last pushed 3d ago), licensed MIT. It adds 103 tokens to every session and 1,855 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
browse-and-evaluate
Use when exploring the ai-agent-skills catalog to find, compare, and evaluate skills before installing. Always use --fields to limit output size and --dry-run before committing to an install.
loop-engineering
Shared loop-engineering reference for COG skills - the agent loop, deterministic verifiers, termination conditions, in-loop context management, and named patterns. Invoke when designing or debugging a skill that iterates (search-verify-retry, scan-until-dry, fetch-retry-gate).
render-airdrop-carousel
Assemble a viral iOS "AirDrop" notification-carousel video ad (≈6–8s, 9:16) from a brand line plus 6–16 real product photos — a native AirDrop share-sheet card ("Brand would like to share a · Decline / Accept") springs up and its preview window CYCLES through the products, landing on a range/lineup payoff with an…
render-3d-product-showcase
Assemble a premium 3D product-showcase ad from a config — four beat clips (an orbiting hero rotation, a macro push-in, a physics reveal, a typographic close) normalized to the brand-color canvas, hard-concatenated in order, closed on a deterministic Playwright brand end card, and mixed under one instrumental bed at…
vfx-text-cursor
Cursor light trail, chromatic rays, and directional flares for word-by-word quote reveals in video intros.
music
Generate, remix, extend, edit, and analyze AI music (Mureka). Triggers on: "音乐", "music", "生成音乐", "generate music", "翻唱", "cover", "混音", "remix", "续写", "extend", "纯音乐", "instrumental", "配乐", "soundtrack", "分轨", "stem", "识别歌词", "recognize lyrics", "作曲", "compose", "create a song", "做一首歌".