Borrowing it
Nothing to install: this file belongs to os-factory/har. 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/os-factory/har/main/.claude/skills/v1-milestone/SKILL.mdgit clone --depth 1 https://github.com/os-factory/harWrote 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/os-factory/har/v1-milestone)<a href="https://agentmods.dev/skills/os-factory/har/v1-milestone"><img src="https://agentmods.dev/badge/skills/os-factory/har/v1-milestone/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/os-factory/har/v1-milestone"><img src="https://agentmods.dev/badge/skills/os-factory/har/v1-milestone.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 | $0.00110 | $0.02085 |
| Opus 5.5 | $0.00044 | $0.00834 |
| Sonnet 5.5 | $0.00022 | $0.00417 |
| Haiku 4.5 | $0.00011 | $0.00209 |
Grade A, and why
v1-milestone 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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
HAR v1.0.0 milestone factory line
Instance of the factory-line template. Program data:
v1-milestone.line.json. This skill stays the executable playbook for the 1.0.0 run. Stacked PRs, GitHub-issue stations, and the car-app jig are this line's tactics — not the primitive. To run a different program, copy a line file, not this skill.
Execute one milestone of the v1.0.0 refactor end-to-end: sync → wave plan → parallel implementation → stacked PRs → gate → handoff.
Source of truth is GitHub: epic #225 and its sub-issues #226–#243 (plus triaged bugs #195–#198). Never duplicate the plan into files; report progress as issue comments and epic checkboxes.
Input: a milestone id M0..M5 (default: the first milestone whose issues are
not all closed).
Milestone map
| Milestone | Issues | Waves (each {} group = one subagent; groups in a wave run in parallel) |
|---|---|---|
| M0 Foundations + 0.x patches | #226 #227 #228 #229 #196 #197 #198 + #195 (skip-ci half only) | Wave 1: {#228} {#196} {#197} {#198} {#195} · Wave 2: {#226} · Wave 3: {#227} {#229} |
| M1 Contract | #230 #231 #232 #233 | Wave 1: {#230} {#233} · Wave 2: {#231} · Wave 3: {#232} |
| M2 Runtime into package | #234 #235 #236 | Wave 1: {#234} split into parallel forks per module (ports/preflight, worktree+launch, provisioning, infra, slot-registry) + one integration fork · Wave 2: {#235} {#236} |
| M3 Adaptation & extensibility | #237 #238 #239 #240 | Wave 1: all four in parallel · Wave 2: integration pass |
| M4 Migration & docs | #241 #243 | Wave 1: both in parallel |
| M5 Release gate | #242 + the v1 → main release PR |
Sequential; ends in handoff for the 1.0.0 release decision |
Waves are ordered by real file conflicts: #226 rewrites the template tree, so
#227/#229 (and anything touching src/templates/) must stack on top of it;
#231 needs #230's env schema; #232 validates both.
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 · 137 lines · 110 tokens per session scan A b67cff72b4f6
v1-milestone is a skill published in the GitHub repository os-factory/har (129 stars, last pushed 3d ago), licensed Apache-2.0. It adds 110 tokens to every session and 2,085 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 2026-08-30.
v1-milestone compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| v1-milestoneos-factory/har | Skill | 129 | 3d ago | Apache-2.0 | A | 110 | Claude Code |
| release-notesjnMetaCode/ai-coding-guide | Skill | 550 | 4d ago | Apache-2.0 | A | 59 | Claude Code, Codex |
| ctxagentis-tools/ctx | Skill | 13 | 2d ago | Apache-2.0 | A | 60 | Claude Code |
| task-final-reportpostmelee/hyper-waterfall | Skill | 82 | 3mo ago | MIT | A | 74 | Claude Code, Codex |
| release-and-changelogduthaho/claudekit | Skill | 97 | 3mo ago | MIT | A | 99 | Claude Code |
| releaseiroha924/mumei | Skill | 2 | 1mo ago | MIT | A | 144 | Claude Code |
| compass-releasecrabbuild/compass | Skill | 175 | 18d ago | none | C | 78 | Claude Code, Codex |