PERT
Program Evaluation & Review Technique
Weighted three-point estimates with critical-path detection. Surfaces float, slack, and which task to actually unblock.
OSS skill · mcp · api
v0.4 · alpha
Mathematical rigour,
for PMOs and the agents that assist them.
Open-source Skills, MCP servers, and APIs that let Claude and other agents reason about projects the way a senior analyst does — with PERT, Monte Carlo, Bayesian updating, TCO and the rest of the kit.
Skills
4
Claude-native
MCP tools
5
stdio · prototype
APIs
REST
FastAPI
Methods
PERT · MC · Bayes
peer-reviewed
§01 / premise
The administrative PMO won't survive agents. The strategic PMO will need them.
We're not selling a replacement. We're shipping the toolbox the next generation of PMO work is built on — kernel open, premium plugins where data integration warrants it, consulting where the analysis is bespoke.
An AI agent can estimate a delivery date in seconds, but it can't judge which task to unblock next. pmo.run gives PMOs and their agents the maths to do both — with every number traceable.
§02 / methods
Maths-proved logic, packaged as tools.
Each method ships as a Skill (for Claude), an MCP server (for any agent), and an HTTP API. Same kernel, three surfaces.
Monte Carlo
Schedule simulation, 10⁵ samples
Replaces single-point dates with distributions. p50 / p90 ship dates, sensitivity per task, and confidence intervals you can defend.
OSS deterministic seed
Bayesian updating
Estimates that learn from delivery
Updates prior beliefs as tickets close. Replaces the "gut feel re-baseline" with an auditable likelihood update.
OSS conjugate priors
TCO
Total cost of ownership, decomposed
License + ops + integration + training + the hidden line items. Used by SIers to defend procurement decisions.
OSS + industry datasets
+ earned-value, throughput accounting, queueing models, risk-adjusted NPV — see /docs
§03 / install
Drop-in for Claude, Cursor, or any MCP client.
No platform lock. Skills load into Claude. The same kernel runs as a local MCP server, or behind your gateway as an HTTP API.
# clone the open-source repo $ git clone https://github.com/lemur47/logic $ cd logic # install the skills for Claude Code $ cp -r skills/* ~/.claude/skills/ # Claude can now reason with PERT claude> what's the critical path on the Q3 plan? → skill: pmo/pert critical: A → B → D → F → G (14.2d) slack: C: 2.1d, E: 0.8d
# after cloning: install + run the server $ uv pip install -e . $ uv run python -m mcp_server.server # or wire it into any MCP client { "mcpServers": { "pmo-logic": { "command": "uv", "args": ["run", "python", "-m", "mcp_server.server"] } } } # prototype · 5 tools over stdio
§04 / open core
Three layers. One contract.
The three-layer core is open source: the core logic and tools stay MIT-licensed. Paid plugins and consulting services add on top — your own proprietary layer.
| Layer | What's in it | Who it's for | License | Pricing |
|---|---|---|---|---|
| OSS Kernel | Skills, MCP servers, APIs. PERT, Monte Carlo, Bayes, EVM, TCO, queueing. | International PMO communities, individual practitioners, contributors. | MIT | free |
| PAID Plugins | Proprietary connectors: Jira Cloud, ServiceNow, SAP, MS Project, Salesforce. Industry datasets, benchmark libraries. | Systems integrators, internal platform teams. | commercial | seat / usage |
| SERVICE Strategic | Bespoke analysis, model calibration, rollout, executive briefings, training programmes. | Consulting firms, large transformation programmes. | contract | retainer |
§05 / for whom
For PMOs evolving from administrators to strategists.
The administrative half of the PMO role — status rollups, variance reports, schedule maintenance — will be done by agents. Our work is to give those agents the same rigorous tools your best analysts use, so the human half can move upstream into strategy.
practitioner
Stop hand-rolling Monte Carlo in Excel. Drop the skill in Claude. Get the same numbers, defensible.
SIer
Plug into your client's Jira / ServiceNow / SAP. Ship licensed integrations under your brand if you need to.
consulting firm
Put your historical data to work with PMO logic and tools, and sharpen your firm's insight.
§06 / start