specify-milestone-starting-state

specify-milestone-starting-state is a skill for Claude Code from uHappyLogic/cairn. It costs 36 tokens per session (1,051 once invoked), scanned A, original, MIT.

A tool that examines a project's current files and state, then records relevant background information in a milestone's requirements document. A milestone is a defined stage of a larger development project.

In plain words
What is it for?
Use it before planning a milestone to document the current code, structure, configuration, and other project context relevant to that milestone.
Why use it?
It gives future planning discussions a factual starting point based on the existing project, without making design decisions on its behalf.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions CLAUDE.md; installed under .agents/ (shared by several agents).

Part of the cairn plugin — 22 skills, 3 agents shipped together

Good fit Use it before planning a milestone to document the current code, structure, configuration, and other project context relevant to that milestone.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/uhappylogic/cairn/specify-milestone-starting-state
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 uHappyLogic/cairn --skill specify-milestone-starting-state
Clone the repo
git clone --depth 1 https://github.com/uHappyLogic/cairn

Made for: Claude Code.

Or install cairn, the plugin that ships this one along with the rest of its 22 skills, 3 agents.

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.

agentmods badge for specify-milestone-starting-state

README.md
[![agentmods](https://agentmods.dev/badge/skills/uhappylogic/cairn/specify-milestone-starting-state/github.svg)](https://agentmods.dev/skills/uhappylogic/cairn/specify-milestone-starting-state)
Your own site
<a href="https://agentmods.dev/skills/uhappylogic/cairn/specify-milestone-starting-state"><img src="https://agentmods.dev/badge/skills/uhappylogic/cairn/specify-milestone-starting-state/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.

agentmods 80×15 button for specify-milestone-starting-state

Your own site · 80×15
<a href="https://agentmods.dev/skills/uhappylogic/cairn/specify-milestone-starting-state"><img src="https://agentmods.dev/badge/skills/uhappylogic/cairn/specify-milestone-starting-state.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,051 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00036 $0.01051
Opus 5 $0.00018 $0.00526
Sonnet 5 $0.00007 $0.00210
Haiku 4.5 $0.00004 $0.00105

Measured 3d ago against content hash d4ee9c8c0ad7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

specify-milestone-starting-state 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 3d 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.

.agents/plugins/cairn/skills/specify-milestone-starting-state/SKILL.md · 96 lines

How it starts

The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.

specify-milestone-starting-state

Reads the milestone goal, explores the project's existing state, and writes a concise summary into the ## Relevant starting state section of requirements.md. The output is reference material — not decisions — to ground the ## Decisions conversation that follows.

Usage

/specify-milestone-starting-state <milestone_id>
  • <milestone_id>: the milestone directory name under milestones/, e.g. milestone_12_user-guide.

Example:

/specify-milestone-starting-state milestone_12_user-guide

Workflow

1. Locate the milestone

Resolve milestones/<milestone_id>/requirements.md. If the file does not exist, stop and report that the milestone was not found — suggest running /define-milestone-goal first.

2. Read the goal

Read requirements.md in full. Extract the ## Goal section. This is the lens for everything that follows — only surface starting state that is directly relevant to achieving or building on that goal.

3. Load the environment and explore the project

Read CLAUDE.md at the workspace root for the project's environment. If it carries no description of the project's domain context or working conventions, suggest the user run /init to enrich it first — richer project context yields a sharper starting-state summary — then proceed with whatever the project reveals.

Extract from CLAUDE.md:

  • The project's domain context — what the project is and how its material is organized; use this to anchor all exploration
  • Working conventions — the practices the project follows
  • Available tools — whether any tools (including MCP tools) are available for deeper inspection
  • How work is verified as done — the project's convention for confirming a deliverable meets its bar

Using the goal as a filter, investigate the areas the project documents in CLAUDE.md. Focus on:

  • Existing artifacts relevant to the goal — find the artifacts, sections, and components whose names or responsibilities overlap with the goal. Read what they expose — their outward-facing surface. Skip internal detail.
  • Existing capabilities — if the goal builds on something that already exists, describe its current state and how other work connects to it.
  • Supporting materials — note any settings, reference data, or structures the milestone will likely touch.
  • Known gaps — if the goal requires something that clearly does not exist yet, state it as a gap in one sentence and move on; do not design its replacement here.

Read the full file on GitHub · 96 lines

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.

  1. 3d ago Changed d4ee9c8c0ad7
  2. 5d ago Changed · -7 lines acff6abd557c
  3. 10d ago First seen · 103 lines · 36 tokens per session scan A 4171f67358d3

Subscribe to this mod's changes

specify-milestone-starting-state is a skill published in the GitHub repository uHappyLogic/cairn (2 stars, last pushed 2d ago), licensed MIT. It adds 36 tokens to every session and 1,051 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

debt-ops-init

Write or refresh a "Tech debt operations" section in the project's AGENTS.md so the team shares one source of truth for debt-ops disciplines. Run ONLY when the user explicitly asks to set up, install, or initialize debt-ops disciplines — never auto-invoke. Idempotent; only the managed section changes, other sections…

bcanfield/agentic-tech-debt · 76 tokens

debt-ops-metrics

Print a debt-ops health summary from the metrics log, covering registration rate, feedback action rate, ADR creation, and AI-authored share. Use when the user asks for "debt-ops metrics", "debt health", "registry stats", or a tech-debt health summary. Read-only, never writes the log.

bcanfield/agentic-tech-debt · 74 tokens

debt-ops-add

Register a deferred decision in the tech-debt registry. Trigger by judgment, not a marker scan, whenever a future reader would ask "why this way?": an unmade decision, stub, loosened type, bypassed check, swallowed error, a default picked "for now", or a TODO/FIXME/HACK/XXX marker. Trigger immediately whenever you…

bcanfield/agentic-tech-debt · 115 tokens

review

Run a full code review on current changes or specified files. Runs ruff lint, review-code agent, and security scan in sequence.

This-HW/claude-code-kit · 29 tokens

plan-task

Structured task planning using Work files. Use for any new feature, bug fix, or project that needs a task breakdown before implementation.

This-HW/claude-code-kit · 29 tokens

scout-consolidation

Launch a Scout consolidation session as a background process. Runs a lighter delta scan — captures what changed since the last run and updates action items and KB.

Raven-Scout/scout-plugin · 36 tokens