project_state_management

project_state_management is a skill for Claude Code, Codex from ApexIQ/skillsmith. It costs 18 tokens per session (549 once invoked), scanned A, original, MIT.

A file-based system for tracking a project's purpose, roadmap, current work, next steps, and known issues. It keeps this information in PROJECT.md, ROADMAP.md, and STATE.md files.

In plain words
What is it for?
Use it to preserve project context, record milestones, track current tasks, and keep the agent aligned across coding sessions.
Why use it?
An AI agent cannot reliably depend on old chat messages when a conversation becomes long or a new session starts. Saved state gives it a durable project reference.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to preserve project context, record milestones, track current tasks, and keep the agent aligned across coding sessions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/apexiq/skillsmith/project_state_management
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 ApexIQ/skillsmith --skill project_state_management
Clone the repo
git clone --depth 1 https://github.com/ApexIQ/skillsmith

Made for: Claude Code, Codex.

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 project_state_management

README.md
[![agentmods](https://agentmods.dev/badge/skills/apexiq/skillsmith/project_state_management/github.svg)](https://agentmods.dev/skills/apexiq/skillsmith/project_state_management)
Your own site
<a href="https://agentmods.dev/skills/apexiq/skillsmith/project_state_management"><img src="https://agentmods.dev/badge/skills/apexiq/skillsmith/project_state_management/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 project_state_management

Your own site · 80×15
<a href="https://agentmods.dev/skills/apexiq/skillsmith/project_state_management"><img src="https://agentmods.dev/badge/skills/apexiq/skillsmith/project_state_management.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 18 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 549 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 $0.00018 $0.00549
Opus 5 $0.00009 $0.00275
Sonnet 5 $0.00004 $0.00110
Haiku 4.5 $0.00002 $0.00055

Measured 7d ago against content hash 753252e166bb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

project_state_management 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 7d 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.

src/skillsmith/templates/.agent/skills/agentic_lifecycle/project_state_management/SKILL.md · 90 lines

What it actually says

Project State Management

This skill prevents "Context Rot" by maintaining a single source of truth for the project's state. AI Agents should read these files to understand where we are without re-reading the entire chat history.

The State Files

  1. PROJECT.md: The high-level "Constitution" of the project.
  2. ROADMAP.md: The strategic plan (Features, Milestones).
  3. STATE.md: The tactical status (Current Task, Next Steps, Known Issues).

1. PROJECT.md (The "Why" and "What")

Create or update .agent/PROJECT.md with:

# Project Name

## Vision
One sentence describing the ultimate goal.

## Tech Stack
- Language: Python/TypeScript
- Framework: FastAPI/Next.js
- Database: Postgres

## Core Principles
1.  Atomic Commits.
2.  Test-Driven Development.
3.  Mobile-First Design.

2. ROADMAP.md (The "When")

Create or update .agent/ROADMAP.md with:

# Roadmap

## Phase 1: MVP [x]
- [x] User Authentication
- [x] Basic Dashboard

## Phase 2: Scale [/]
- [ ] Database Migration
- [ ] Redis Caching

## Phase 3: Polish [ ]
- [ ] UI Animations
- [ ] Dark Mode

3. STATE.md (The "Now")

CRITICAL: Update this file after every atomic step.

# Current State

**Last Updated:** YYYY-MM-DD HH:MM

## Current Objective
Implementing the "Forgot Password" flow.

## Context
- We have the API endpoint `/auth/forgot`.
- We need the frontend form in `ForgotPassword.tsx`.

## Next Steps
1.  Create `ForgotPassword.tsx` form.
2.  Connect to API.
3.  Verify email delivery.

Instructions for Agents

  1. Start of Session: Always read STATE.md to orient yourself.
  2. End of Task: Always update STATE.md with your progress.
  3. Confusion: If STATE.md contradicts the code, trust the code but update STATE.md immediately.
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. 7d ago First seen · 90 lines · 18 tokens per session scan A 753252e166bb

Subscribe to this mod's changes

project_state_management is a skill published in the GitHub repository ApexIQ/skillsmith (5 stars, last pushed 5mo ago), licensed MIT. It adds 18 tokens to every session and 549 once invoked, about $0.0001 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 2026-09-03.

Related

Other skills, from other repositories

knowledge-curation

Context priming before work (bd prime) and self-reflection after completion to extract patterns, gotchas, and decisions into the knowledge base.

a5c-ai/babysitter · 33 tokens

alive-bundle

Create, manage, and graduate bundles -- the unit of focused work within a walnut.

alivecontext/alive · 20 tokens

duduclaw-platform

Use the DuDuClaw MCP tools (persistent memory, shared wiki, task board, channel messaging) when the user asks to remember something across sessions, share knowledge with their team's AI employees, manage tasks, or message someone on LINE/Telegram/Discord/Slack. Requires a running DuDuClaw gateway (npx duduclaw onboard…

zhixuli0406/DuDuClaw · 81 tokens

proactive-memory

Turn repeated failures, corrections, and recurring requests into durable follow-up work.

aaronnat23/disp8ch · 0 tokens

duduclaw

Use DuDuClaw — a self-hosted AI-employee platform — for cross-session memory, team-shared wiki knowledge, task boards, and messaging humans over LINE/Telegram/Discord/Slack. Applies when the user mentions DuDuClaw, asks their agent to remember things durably, or wants to reach people on messaging channels from an…

zhixuli0406/DuDuClaw · 77 tokens

memory-search

PROACTIVELY search conversation history and semantic memory BEFORE starting new work. Use at the START of any non-trivial task to recall prior decisions, avoid repeating past discussions, and reuse what was already learned. Also use when the user asks to "search memory", "what did we discuss", "remember when", "find…

23blocks-OS/ai-maestro-plugins · 90 tokens