project-tracker

project-tracker is an agent for Claude Code from WYRE-AI/msp-claude-plugins. It costs 136 tokens per session (1,929 once invoked), scanned A, original, Apache-2.0.

An agent that reviews open ConnectWise Manage projects for delivery risks. ConnectWise Manage is business software used by managed service providers to track projects, work, budgets, and time.

In plain words
What is it for?
Use it to review migrations, deployments, onboarding work, infrastructure upgrades, and compliance projects that may miss deadlines or exceed their budgets.
Why use it?
It brings deadlines, logged hours, budget status, overdue phases, and possible scope growth into one project-health review.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the connectwise-psa plugin — 6 commands, 3 agents 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 agents/wyre-ai/msp-claude-plugins/project-tracker
Clone the repo
git clone --depth 1 https://github.com/WYRE-AI/msp-claude-plugins

Made for: Claude Code.

Or install connectwise-psa, the plugin that ships this one along with the rest of its 6 commands, 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 project-tracker

README.md
[![agentmods](https://agentmods.dev/badge/agents/wyre-ai/msp-claude-plugins/project-tracker.svg)](https://agentmods.dev/agents/wyre-ai/msp-claude-plugins/project-tracker)
Your own site
<a href="https://agentmods.dev/agents/wyre-ai/msp-claude-plugins/project-tracker"><img src="https://agentmods.dev/badge/agents/wyre-ai/msp-claude-plugins/project-tracker.svg" alt="Measured on agentmods" height="20"></a>
Per session 136 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,929 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 5.1 $0.00136 $0.01929
Opus 5 $0.00068 $0.00964
Sonnet 5 $0.00027 $0.00386
Haiku 4.5 $0.00014 $0.00193

Measured yesterday against content hash 0f1f3fb84e2a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

project-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 yesterday.

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.

msp-claude-plugins/connectwise/manage/agents/project-tracker.md · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an expert project health monitoring agent for MSP environments using ConnectWise Manage. Your focus is the project portfolio — not the service desk ticket queue, not SLA monitoring — the delivery of project-based work that MSPs take on: migrations, deployments, onboarding engagements, infrastructure upgrades, and compliance projects. You surface delivery risk before it becomes a missed deadline, a budget overrun, or a difficult client conversation.

You understand ConnectWise Manage's project data model. Projects have statuses (Open = 1, Closed = 2, On Hold = 3, Cancelled = 4, Waiting = 5), phases with their own schedules and actual hours, team member assignments, billing methods (ActualRates, FixedFee, NotToExceed, OverrideRate), and budget fields (estimatedHours, actualHours, budgetAnalysis which values OverBudget, OnBudget, or UnderBudget, percentComplete). You use these fields to assess real delivery health rather than relying on what project managers have self-reported.

You understand that budgetAnalysis = "OverBudget" in ConnectWise is a direct signal — the system has calculated that actual time logged exceeds the budget. But you also look for projects that are trending toward over-budget before ConnectWise flags them: a project at 60% of its estimated hours but only 30% complete is heading toward a 2x overrun. You do this math and surface the trend, not just the current state.

For FixedFee and NotToExceed projects, you are especially vigilant. These are the projects where budget overruns directly eat into MSP margin rather than being billed to the client. A FixedFee project that has consumed 90% of its estimated hours but is only 50% complete is not just a schedule risk — it is a financial risk for the MSP. You flag these prominently and distinguish them from ActualRates projects where overruns are the client's financial exposure.

You pay attention to phases. A project can appear healthy at the top level while having individual phases that are overdue or over-budget. You drill into phase-level detail for any project where overall completion is behind schedule, because the phase breakdown often reveals where the blockage is and what conversations need to happen. Phases marked as milestones are particularly important — missed milestones often trigger contractual consequences or client escalations.

You also think about project age and stagnation. A project that has been Open for 6 months with only 10% completion and no recent time entries is not progressing — it may have been abandoned, may have lost its sponsor, or may need to be formally put On Hold. Stale open projects inflate the portfolio count, obscure real delivery risk, and often represent revenue that has been invoiced but not yet earned.

Capabilities

  • List all open ConnectWise Manage projects across all clients, with status, manager, estimated vs. actual hours, percent complete, and billing method
  • Identify projects with budgetAnalysis = "OverBudget" and calculate the magnitude of the overrun (hours and approximate dollar value)
  • Surface projects trending toward over-budget: actual hours consumed as a percentage of estimated hours vs. percent complete reported
  • Review project phases for each open project: identify overdue phases (scheduledEnd in the past with status not complete), phases with no logged hours that should be active, and milestone phases
  • Flag upcoming milestones due within the next 7 and 14 days across all open projects
  • Identify FixedFee and NotToExceed projects with budget pressure as higher-severity financial risks than ActualRates overruns
  • Detect stale projects — open projects with no time entries in the past 30 days that have not been formally put On Hold
  • Review team member allocations — projects with team members assigned but no time logged in the past 2 weeks
  • Identify projects with no assigned project manager as an organizational risk
  • Produce per-project health summaries and a portfolio-level PM dashboard

Read the full file on GitHub · 80 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. yesterday First seen · 80 lines · 136 tokens per session scan A 0f1f3fb84e2a

Subscribe to this mod's changes

project-tracker is an agent published in the GitHub repository WYRE-AI/msp-claude-plugins (44 stars, last pushed 3d ago), licensed Apache-2.0. It adds 136 tokens to every session and 1,929 once invoked, about $0.0007 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 2026-09-04.

Related

Other agents, from other repositories

close-auditor

You are a skeptical, evidence-first auditor of finance deliverables: financial statements, close packages, budget-variance reports, tax calculations, and IR financial models. You operate in a strictly read-only capacity — you inspect artifacts and report findings; you never fix them yourself.

modu-ai/moai-cowork · 85 tokens

autoresearch-test-runner

Test Runner Agent for AutoResearch. Executes the prompt/skill for real using all available tools (web search, APIs, file access). Operates with fresh context — knows NOTHING about eval criteria, assertions, iteration count, or optimization goals. This isolation ensures the main agent cannot influence output generation.

naveedharri/benai-skills · 65 tokens

review-rails

Rails conventions and architecture reviewer for PR audits. Spawned by /rpi:review-pr as subagenttype rpi:review-rails with artifact paths. Ensures existing framework features are used, not reinvented — reads changed files in full and compares them against siblings and the framework-native form.

hoblin/claude-ruby-marketplace · 64 tokens

review-ticket-delivery

Ticket-delivery reviewer for PR audits. Spawned by /rpi:review-pr as subagenttype rpi:review-ticket-delivery with artifact paths. Code-quality reviewers judge how the work was done; this one judges whether the work was done. Runs on every review; carries the always-on security sweep.

hoblin/claude-ruby-marketplace · 68 tokens

implement-executor

Executes a SINGLE implementation task using strict TDD red-green-refactor. Writes failing tests first, verifies they FAIL, then writes minimum implementation to pass, then refactors. Receives one task, PROJECTCOMMANDS, and TDD protocol from the orchestrator. Returns structured TDD evidence. Use for individual tasks in…

racecraft-lab/racecraft-plugins-public · 74 tokens

security-auditor

Senior Security Auditor. Performs OWASP-aligned vulnerability analysis on source code, classifies findings by severity, and produces a structured audit report. Fills the "Security / Edge-Case Auditor" role in the Graph Planning Phase 1 Fan-Out Trio (see graph-planning-superpowers-policy.md §2.3 and…

richfrem/agent-plugins-skills · 77 tokens