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 milestonesgit 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/milestones)<a href="https://agentmods.dev/skills/alunduil/alunduil-chezmoi/milestones"><img src="https://agentmods.dev/badge/skills/alunduil/alunduil-chezmoi/milestones/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/milestones"><img src="https://agentmods.dev/badge/skills/alunduil/alunduil-chezmoi/milestones.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 | $0.00051 | $0.01055 |
| Opus 5 | $0.00026 | $0.00528 |
| Sonnet 5 | $0.00010 | $0.00211 |
| Haiku 4.5 | $0.00005 | $0.00105 |
Grade A, and why
milestones 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 12d 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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Milestones
A milestone is a finite, scoped group of issues converging on a shipping or closing event. If it doesn't converge, it's a label.
Pick one axis per project
- Release-anchored — name = the version it targets:
v1.0.0,v1.1.0(semver), or1.0.0.0(PVP). Best when the project ships releases. Pre-stable work collapses to one placeholder —v0.1.0(semver) or0.0.1.0(PVP) — since those names already mean "not yet production-ready"; don't fan out across pre-1.0 versions. - Date-anchored — name = the calendar window:
2026-Q2,2026-05,Sprint 23. Best when work is time-bounded. - Theme-anchored — name = the outcome:
Auth overhaul,Public beta. Best for project phases not pegged to a release or window.
Don't mix axes within one project — v1.1.0 and 2026-Q2 and
Auth overhaul together leaves contributors guessing where to file.
Pick one and inherit it for the next milestone.
Description: outcome, not inventory
The description states the user-visible outcome the milestone delivers — present-tense, the way you'd phrase an OKR objective. Issues are the actions; the milestone is what those actions add up to.
- Outcome-shaped: "Auth flows can be configured without code changes." "Cold-start latency under 200ms on the free tier."
- Not outcome-shaped: "Refactor auth middleware." (That's a task — file as an issue.) "All v1.1 work." (Restates the title — adds nothing.) A list of issue links. (Readers can see those.)
- Optional: a short non-goals line to bound scope.
The description is the contract the convergence test runs against — "does closing this issue advance this outcome?"
When not to use a milestone
- Categorical tag (area, type, priority) → label.
- Ongoing planning surface across many issues → Project board.
- Ad-hoc "see also" between two issues → plain
#Nmention or theissue-linksskill.
Due dates
- Release- / date-anchored: set the due date to the release date or window end. Slipping the date is fine; missing data is worse than imprecise data — the rollup needs a horizon.
- Theme-anchored: skip unless there's a real deadline.
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.
- 12d ago First seen · 105 lines · 51 tokens per session scan A 948eb62672cc
milestones is a skill published in the GitHub repository alunduil/alunduil-chezmoi (2 stars, last pushed today), licensed 0BSD. It adds 51 tokens to every session and 1,055 once invoked, about $0.0003 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
work-on
End-to-end workflow for shipping a GitHub issue. Assesses complexity, builds a tailored workflow, and orchestrates skills from research through PR.
project-manager
Use when creating, updating, or triaging GitHub issues. Writes issues from a product perspective — user stories, acceptance criteria, context, and dependencies — without prescribing implementation.
share-plan
Use when sharing an implementation plan to a GitHub issue. Formats plans with collapsible details sections so issues are scannable but comprehensive.
new-project
Bootstrap a new repository by composing the stack, license, mise, lefthook, dprint, CI, agent files, GitHub settings, and first release skills. Use when creating a project.
acli
Use the Atlassian acli for Jira work items, sprints, boards, and Confluence pages with OAuth or token auth, JQL-bounded reads, and confirmed writes. Use for Jira or Confluence work.
github-issues
Plan and manage GitHub issues with gh: turn audit findings into deduplicated prioritized issue drafts, preserve acceptance evidence, and verify authorized creation, edits, dependencies, labels, comments, or closure. Use for GitHub issues.