A persistent way to track multi-session development work, including unfinished tasks, project context, and architectural decisions.

Use it to record milestones, resume a project, review what remains, and coordinate claimed tasks when working with others.

It prevents important decisions and the next steps from being lost when work pauses or moves between conversations.

milestone — Skill for Claude Code by j4rk0r

Install

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.

Any agent

npx skills add j4rk0r/claude-skills --skill milestone

Clone the repo

git clone --depth 1 https://github.com/j4rk0r/claude-skills

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/j4rk0r/claude-skills/milestone/github.svg)](https://agentmods.dev/skills/j4rk0r/claude-skills/milestone)

Your own site

<a href="https://agentmods.dev/skills/j4rk0r/claude-skills/milestone"><img src="https://agentmods.dev/badge/skills/j4rk0r/claude-skills/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/j4rk0r/claude-skills/milestone"><img src="https://agentmods.dev/badge/skills/j4rk0r/claude-skills/milestone.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 164 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,906 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00164	$0.03906
Opus 5	$0.00082	$0.01953
Sonnet 5	$0.00033	$0.00781
Haiku 4.5	$0.00016	$0.00391

Measured 12d ago against content hash 8f080f420687, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

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 12d ago.

The scan reads SKILL.md. This mod also ships 4 executable files (references/context-guard.sh, references/milestone-new-session.sh, references/milestone-sync.sh, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/milestone/SKILL.md · 119 lines

How it starts

The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Milestone v2 — Persistent Development Context

Pattern: SKILL.md = Process (state machine, checkpoints). references/ = Tool (exact procedures, decision trees). Body teaches WHEN; references teach HOW.

Overview

Portable skill for multi-session development tracking. Manages state ([ ]/[>]/[~]/[x]/[-]), history (## Contexto), decisions, and memory snapshots. Zero external dependencies. Integrations (Monday/Jira/Linear/Slack) live in separate skills that observe .milestones/*.md via hooks. Optional team mode (R13 + R14): opt-in via .milestones/config.yml makes the milestone a single shared source of truth git-synced to a canonical branch (R13) AND requires an atomic claim before starting any subtask so two members can never accidentally pick the same one (R14). Además, un sync de índice (H4, git-sync.md §12) descubre milestones que otro creó antes de listar o crear: al hacer /milestone init avisa si el nombre ya existe (y quién lo creó, cuándo) en vez de duplicar; al hacer /milestone (list) muestra los milestones remotos que aún no tienes en local. Todo degrada a no-op cuando no está configurado, así que la promesa zero-dependency se mantiene. Optional central storage (R13 §2b): opt-in by placing the config in the central memories repo (~/.claude/projects/<key>/milestones/config.yml) instead of the project repo — the client repo stays 100% clean of internal planning.

Use when: multi-session work OR need to resume context OR architectural decisions to remember. Otherwise → TodoWrite/Plan.

Critical anti-patterns (TOP 3 — full list → `references/anti-patterns.md`)

NEVER mark [x] without explicit human approval post-QA. "pasa a la siguiente" / "ok" / "listo" are NOT approval — only "apruebo X.Y" / "marca como terminada" / "confirmed" count. Failed QA → stays [~], never reverts.
NEVER flip state based on intent. Only advance AFTER verified evidence on disk (grep confirms symbol/route/method, git status lists file, phpcs/test pass). Prevents phantom progress when sessions get cut mid-work.
NEVER close session with code changes without R11 session-end protocol. Drift inherits to next start. Verify evidence → Edit milestone → ## Contexto entry → refresh snapshot.

Read the full file on GitHub · 119 lines

Files

What ships with it

26 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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 · 119 lines · 164 tokens per session scan A 8f080f420687

Subscribe to this mod's changes

milestone is a skill published in the GitHub repository j4rk0r/claude-skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 164 tokens to every session and 3,906 once invoked, about $0.0008 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.

Claude Code Memory and context Planning agent-skills ai-tools anthropic claude claude-skills

shipkit-work-memory

Log session progress and save resume state. Infers from conversation and git. Triggers: 'log progress', 'session summary', 'checkpoint', 'save progress', 'end session'.

stefan-stepzero/shipkit · 42 tokens

shipkit-claude-md

Update CLAUDE.md with learnings, preferences, or project context. Use when user says "update claude.md", "add to claude.md", or wants to persist something.

stefan-stepzero/shipkit · 45 tokens

init-project-memory

Use when the user says "init memory", "set up memory", "scaffold memory", "init project memory", or invokes /init-project-memory — creates the .claude/ session memory system in a new project.

jkm-4314/claude-code-skills · 48 tokens

session-update

Use when the user says "update session", "log progress", "checkpoint session", or invokes /session-update — especially before /clear or handoff.

jkm-4314/claude-code-skills · 33 tokens

compact-manual

Claude Code skill for deterministic context compaction. Compresses the current Claude Code session to the clipboard for a manual rewind+paste workflow. A deterministic alternative to /compact that extracts literal dialog and truncates only tool outputs — no LLM summarization. Use when the user says 'compact the…

mario-hernandez/claude-compact-manual · 81 tokens

Vizra ADK Memory System

Implement persistent memory, session context, and vector memory (RAG) for AI agents.

vizra-ai/vizra-adk · 24 tokens