state-tracker

state-tracker is a skill for Claude Code, Codex from YoungjaeDev/my-claude-plugins. It costs 80 tokens per session (1,283 once invoked), scanned B, original, MIT.

A skill for reading and updating .claude/state/spec.json, a project file that summarizes specifications and their linked GitHub issues or pull requests. It tracks work that is in progress or completed.

In plain words
What is it for?
Use it to check what specification work is in flight, see its linked issue or pull request, and maintain the aggregate state cache.
Why use it?
It provides one quick view of specification work instead of requiring you to inspect many specification files and their metadata.

Skill for Claude CodeCodex

Part of the dev plugin — 12 skills shipped together

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.

agentmods
npx agentmods add skills/youngjaedev/my-claude-plugins/state-tracker
Any agent
npx skills add YoungjaeDev/my-claude-plugins --skill state-tracker
Clone the repo
git clone --depth 1 https://github.com/YoungjaeDev/my-claude-plugins

Made for: Claude Code, Codex.

Or install dev, the plugin that ships this one along with the rest of its 12 skills.

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 state-tracker

README.md
[![agentmods](https://agentmods.dev/badge/skills/youngjaedev/my-claude-plugins/state-tracker.svg)](https://agentmods.dev/skills/youngjaedev/my-claude-plugins/state-tracker)
Your own site
<a href="https://agentmods.dev/skills/youngjaedev/my-claude-plugins/state-tracker"><img src="https://agentmods.dev/badge/skills/youngjaedev/my-claude-plugins/state-tracker.svg" alt="Measured on agentmods" height="20"></a>
Per session 80 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,283 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. Scan, not verified.
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 $0.00080 $0.01283
Opus 5 $0.00040 $0.00642
Sonnet 5 $0.00016 $0.00257
Haiku 4.5 $0.00008 $0.00128

Measured today against content hash a056f6f26538, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

state-tracker scanned grade B with 1 finding 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 today.

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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

2. `find .claude/spec -maxdepth 1 -name '*.md' -not -name '_template.md'`.
plugins/dev/skills/state-tracker/SKILL.md · 108 lines

How it starts

The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.

state-tracker

.claude/state/spec.json is a one-file aggregate of the project's spec/issue/PR work pipeline. It exists so an LLM (or human) can answer "what's currently in flight, and against which spec?" with a single Read — no find over .claude/spec/ plus per-file frontmatter parse.

Ships with the dev plugin; install via marketplace. Operates on the current repo's .claude/state/spec.json.

SSOT relationship

Source Authority When it wins
.claude/spec/*.md frontmatter (status:) SSOT Always — the spec file is the truth
.claude/state/spec.json aggregate cache Faster lookup; if it conflicts with frontmatter, regenerate from frontmatter

The cache is regeneratable any time via init (scan spec dir + frontmatter aggregate). Direct edits are allowed but rare — prefer the 4 ops below.

Schema (versioned JSON)

{
  "schema": 1,
  "updated_at": "<ISO 8601>",
  "in_progress": [
    {
      "spec": ".claude/spec/<YYYY-MM-DD>-<slug>.md",
      "section": "<spec internal anchor, optional>",
      "linked": { "issue": <number or null>, "pr": <number or null> },
      "description": "<spec 'Goal' first line, or user-provided one-liner>"
    }
  ],
  "completed": [
    {
      "spec": ".claude/spec/<YYYY-MM-DD>-<slug>.md",
      "linked": { "issue": <number or null>, "pr": <number or null> },
      "description": "<same as above>",
      "completed_at": "<YYYY-MM-DD>",
      "merge_sha": "<short SHA, 7 chars>"
    }
  ]
}

Operations

read — print current state

  1. If .claude/state/spec.json does not exist → print empty state ({ "in_progress": [], "completed": [] }) and inform the user. Do NOT auto-create; ask if they want init.
  2. Read and pretty-print. Highlight in_progress first.

init — regenerate from spec frontmatter (one-shot)

  1. Confirm with user (AskUserQuestion) — this overwrites the file. Default: cancel.
  2. find .claude/spec -maxdepth 1 -name '*.md' -not -name '_template.md'.
  3. For each spec file, parse YAML frontmatter (best effort):
    • status: draft | in-progress | merged → bucket selection
    • ## Goal first non-empty line → description
    • Optional issue: / pr: keys → linked
  4. Write .claude/state/spec.json with schema: 1 and updated_at = now.
  5. Print summary: N in-progress, M completed.

Read the full file on GitHub · 108 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. today Changed a056f6f26538
  2. 5d ago First seen · 108 lines · 80 tokens per session scan B f63fdccd18a5

Subscribe to this mod's changes

state-tracker is a skill published in the GitHub repository YoungjaeDev/my-claude-plugins (2 stars, last pushed yesterday), licensed MIT. It adds 80 tokens to every session and 1,283 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). 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

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens