Borrowing it
Nothing to install: this file belongs to haakonbull/autosprint. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/haakonbull/autosprint/master/.claude/skills/grill-waypoint-from-issue/SKILL.mdgit clone --depth 1 https://github.com/haakonbull/autosprintWrote 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/haakonbull/autosprint/grill-waypoint-from-issue)<a href="https://agentmods.dev/skills/haakonbull/autosprint/grill-waypoint-from-issue"><img src="https://agentmods.dev/badge/skills/haakonbull/autosprint/grill-waypoint-from-issue/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/haakonbull/autosprint/grill-waypoint-from-issue"><img src="https://agentmods.dev/badge/skills/haakonbull/autosprint/grill-waypoint-from-issue.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 | $0.00093 | $0.02066 |
| Opus 5.5 | $0.00037 | $0.00826 |
| Sonnet 5.5 | $0.00019 | $0.00413 |
| Haiku 4.5 | $0.00009 | $0.00207 |
Grade A, and why
grill-waypoint-from-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 2mo 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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Build <target_repo>/autosprint/waypoint.md from a GitHub issue. A waypoint is a user-set intermediate target the autosprint loop aims at exclusively until reached; importing one from a tracked issue bridges "we use GitHub issues as backlog" and "we use autosprint to grind toward goals" without manual transcription.
What this skill is NOT
It does not replace the planner. The waypoint defines what state to reach; the autosprint Plan phase decomposes the gap into sprintable tasks. This skill only writes the waypoint — pointing the loop at the issue. Decomposition happens when the user runs autosprint plan or autosprint run.
It does not modify the GitHub issue (no labels, no comments, no close). The issue and the waypoint are linked by reference (the waypoint carries a Tracks: line) but stay independent. The user closes the issue manually after reviewing what the loop produced.
It is single-issue, single-waypoint. A waypoint is by design a focused sub-goal; if the user wants to address multiple issues, they run the skill once per issue (in sequence, after each waypoint reaches and gets reviewed).
Before starting
-
Verify prerequisites.
- Run
gh auth status. If not authenticated, stop and tell the user to rungh auth loginfirst. - Confirm we are inside an autosprint-initialised repo: check that
<target_repo>/autosprint/config.tomlexists. If not, stop and recommendautosprint initfirst. - Check whether
autosprint/waypoint.mdalready exists. If yes, ask: replace it, abort, or rename existing towaypoint.md.pausedbefore writing the new one? Default to abort on EOF.
- Run
-
Confirm the repo context. Run
gh repo view --json nameWithOwner,urlto confirm which GitHub repoghresolves to from the current directory. If the user expected a different repo, stop and let themcdfirst or pass--repo owner/nametoghcalls below.
Pick the issue
Two flows, depending on how the skill is invoked:
- Direct (
/grill-waypoint-from-issue 42or with a URL like…/issues/42): parse the number, skip to "Fetch the issue". - No argument: list open issues so the user can pick:
Display the list, ask the user for the number. Accept just the integer orgh issue list --state open --limit 20 --json number,title,labels --template '{{range .}}#{{.number}} — {{.title}} {{range .labels}}[{{.name}}] {{end}}\n{{end}}'#42. Refuseclosedissues with a soft warning — closed issues usually mean done, and importing them into a waypoint is rarely what the user wants. If the user insists, proceed.
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.
- 2mo ago First seen · 138 lines · 93 tokens per session scan A b5428a96414b
grill-waypoint-from-issue is a skill published in the GitHub repository haakonbull/autosprint (5 stars, last pushed 4d ago), licensed MIT. It adds 93 tokens to every session and 2,066 once invoked, about $0.0004 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.
grill-waypoint-from-issue compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| grill-waypoint-from-issuehaakonbull/autosprint | Skill | 5 | 4d ago | MIT | A | 93 | Claude Code |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |