decision-tracker

decision-tracker is a skill for Claude Code, Codex from shakestzd/contextune. It costs 46 tokens per session (4,010 once invoked), scanned A, original, MIT.

A Git-based record of project changes, previous work sessions, decisions, and current repository state. Git is a system that records file changes and versions over time.

In plain words
What is it for?
Use it to ask what changed since the last session, inspect commits and file changes, recover past decisions, or check project state before editing files.
Why use it?
It helps prevent outdated assumptions and repeated work by showing what changed, what was decided, and what is currently uncommitted or on another branch.

Skill for Claude CodeCodex

Part of the contextune plugin — 8 skills, 14 commands, 5 agents, 6 hooks, 1 MCP server 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/shakestzd/contextune/decision-tracker
Any agent
npx skills add shakestzd/contextune --skill decision-tracker
Clone the repo
git clone --depth 1 https://github.com/shakestzd/contextune

Made for: Claude Code, Codex.

Or install contextune, the plugin that ships this one along with the rest of its 8 skills, 14 commands, 5 agents, 6 hooks, 1 MCP server.

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 decision-tracker

README.md
[![agentmods](https://agentmods.dev/badge/skills/shakestzd/contextune/decision-tracker.svg)](https://agentmods.dev/skills/shakestzd/contextune/decision-tracker)
Your own site
<a href="https://agentmods.dev/skills/shakestzd/contextune/decision-tracker"><img src="https://agentmods.dev/badge/skills/shakestzd/contextune/decision-tracker.svg" alt="Measured on agentmods" height="20"></a>
Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,010 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00046 $0.04010
Opus 5 $0.00023 $0.02005
Sonnet 5 $0.00009 $0.00802
Haiku 4.5 $0.00005 $0.00401

Measured 4d ago against content hash 31d76f73ed01, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

decision-tracker 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 4d 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.

skills/decision-tracker/SKILL.md · 666 lines

How it starts

The opening of the file, as written. The whole thing — 666 lines — stays where its author put it; the contents beside it link to each section on GitHub.

State Tracker - Git-Powered Session & State Awareness

Purpose: Provide Claude with complete awareness of project state using git as source of truth, preventing stale mental models and redundant work.

What This System Tracks:

  1. In-Session State (real-time)

    • File modifications (git diff)
    • Uncommitted changes (git status)
    • Current branch and commit
  2. Between-Session Context (differential)

    • What happened since last session
    • Commits made (by you or others)
    • Files changed externally
    • Branch switches
  3. Historical Decisions (queryable)

    • Past research findings
    • Architectural decisions
    • Implementation plans

Token Overhead:

  • In-session checks: ~200-500 tokens (only when files change)
  • Between-session context: ~1-2K tokens (differential only)
  • Decision queries: ~2-5K tokens (selective loading)
  • Total: <5K tokens vs 50K+ full reload

When This Skill Activates

Auto-activates when you detect:

State Queries:

  • "what changed since last session?"
  • "show me what happened"
  • "what's the current state?"
  • "what files did we work on?"
  • "what commits were made?"

Before File Operations:

  • PreToolUse hook activates automatically
  • Checks if file changed externally
  • Warns before Edit/Write if file is stale

Before Duplicating Work:

  • "research X" → Check if already researched
  • "decide on Y" → Check if already decided
  • "plan Z" → Check if plan exists

Your Workflow When This Skill Activates

If User Asks "What Changed?"

Run the manual status script:

./scripts/session-status.sh

This shows:

  • Git activity since last session
  • Current working directory status
  • Decision tracking summary

Token cost: ~500 tokens for complete state summary

If You're About to Edit a File

Trust the PreToolUse hook:

  • It automatically checks git status
  • If file changed externally, you'll see warning
  • Follow the recommendation: Re-read before editing

Don't manually check git status - hook does it automatically!

Read the full file on GitHub · 666 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. 4d ago First seen · 666 lines · 46 tokens per session scan A 31d76f73ed01

Subscribe to this mod's changes

decision-tracker is a skill published in the GitHub repository shakestzd/contextune (5 stars, last pushed 8mo ago), licensed MIT. It adds 46 tokens to every session and 4,010 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

media-ingest

Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.

garrytan/gbrain · 52 tokens

mem0-oss-to-platform

Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…

mem0ai/mem0 · 273 tokens

Cortex

Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…

danielmiessler/LifeOS · 196 tokens

agent-memory

../../../engineering/agent-memory/skills/agent-memory/SKILL.md.

alirezarezvani/claude-skills · 0 tokens

memory

Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.

opensquilla/opensquilla · 44 tokens

ha-data-stores

Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…

shiwenwen/hope-agent · 115 tokens