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/how-far/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/how-far)<a href="https://agentmods.dev/skills/haakonbull/autosprint/how-far"><img src="https://agentmods.dev/badge/skills/haakonbull/autosprint/how-far/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/how-far"><img src="https://agentmods.dev/badge/skills/haakonbull/autosprint/how-far.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 | $0.00127 | $0.01478 |
| Opus 5.5 | $0.00051 | $0.00591 |
| Sonnet 5.5 | $0.00025 | $0.00296 |
| Haiku 4.5 | $0.00013 | $0.00148 |
Grade A, and why
how-far 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Estimate how far the codebase has travelled toward autosprint/destination.md and report it as a scannable status table. autosprint drives toward the destination along an approved route; this skill is the odometer — a quick read of how much of the target state is already real, and how far is left to go.
This is the measurement companion to grill-destination and grill-plan. grill-destination sharpens the destination; grill-plan sharpens the next steps; how-far measures the distance still to travel. It is the inverse of grill-destination's mature-repo mode — that mode drafts a destination from the code; this one measures the code against the destination.
What this skill is NOT
- It does not plan. Proposing what to do next is the Plan phase's job (
autosprint plan) andgrill-plan's. This skill only reports where things stand. - It does not edit
destination.md. Sharpening the destination isgrill-destination's job. - It does not impose its own rubric. The rows are the requirements stated in destination.md — nothing more. If a dimension you care about (test coverage, deployment, a refactor) is not a row, that is because destination.md does not state it as a goal — which is itself a useful finding (see below).
- It does not emit a percentage. Per-requirement status is categorical; "73 % done" is a vibe an LLM cannot calibrate, and it drifts optimistic.
Before starting
- Read
<target_repo>/autosprint/destination.mdin full — both the human-authored spec and the## AI-generated subgoalssection. This is the subject. - Read
<target_repo>/autosprint/adr.mdfor context — technical decisions already made. ADRs are how, not what; they do not become rows. - Read the actual code. This is the load-bearing step. Every status you assign must be verified against real source and tests — not inferred from destination.md's wording or from a first impression.
Method
1. Decompose destination.md into requirements
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 · 68 lines · 127 tokens per session scan A 1fce6ea05393
how-far is a skill published in the GitHub repository haakonbull/autosprint (5 stars, last pushed 4d ago), licensed MIT. It adds 127 tokens to every session and 1,478 once invoked, about $0.0005 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.
how-far compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| how-farhaakonbull/autosprint | Skill | 5 | 4d ago | MIT | A | 127 | 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 |