Baltor Get started

Deterministic skills

Records, schedules and budgets

Critical paths, earned value, shift rosters, appointment slots and retention dates as pure functions of JSON input. Each kit ships a known good example and a known wrong example its command refuses.

7 shown here, each at the exact version the library release of October 9, 2026 serves.

What to watch for

  • A schedule with a cycle has no critical path; the calculation must refuse it.
  • Retention periods count from a trigger date that differs by record class.
  • A roster that ignores minimum rest between shifts looks complete and is wrong.

Components

  1. Milestone status report with slippage and dependency conflicts

    milestone_status_report

    Classify each milestone as complete on time, complete late, green, amber, red or overdue from baseline, forecast and actual dates, flag forecasts that precede a predecessor, and write status lines.

    Runs with
    Python 3.10 or later
    Command
    python3 milestone_status_report.py < input.json

    Code moduleMIT12 files, 60.0 KBruns commands

  2. Records retention and disposition date calculator

    records_retention_schedule

    Apply a retention schedule to records: find each trigger date, add the retention period, and mark records due, due soon, on legal hold, waiting for their trigger or retained, with file names checked against a naming pattern.

    Runs with
    Python 3.10 or later
    Command
    python3 records_retention_schedule.py < input.json

    Code moduleMIT12 files, 61.4 KBruns commands

  3. Shift roster builder with skills, hours and rest limits

    shift_roster_builder

    Assign staff to shifts while respecting required skills, unavailable dates, overlapping shifts, minimum rest, weekly hour limits and shift count limits, and explain every unfilled position.

    Runs with
    Python 3.10 or later
    Command
    python3 shift_roster_builder.py < input.json

    Code moduleMIT12 files, 62.1 KBruns commands

  4. Appointment slot allocator for providers and rooms

    appointment_slot_allocator

    Place appointment requests into providers' free time by priority, service, date window, duration, buffer and preferred provider, and report what could not be placed and why.

    Runs with
    Python 3.10 or later
    Command
    python3 appointment_slot_allocator.py < input.json

    Code moduleMIT12 files, 68.6 KBruns commands

  5. Section enrollment allocator with prerequisites and waitlists

    section_enrollment_allocator

    Seat students in course sections by priority group and registration time, honouring capacity, prerequisites, one section per course and time-block clashes, with ordered waitlists.

    Runs with
    Python 3.10 or later
    Command
    python3 section_enrollment_allocator.py < input.json

    Code moduleMIT12 files, 67.6 KBruns commands

  6. Program capacity, staffing and break-even budget

    program_capacity_budget

    Compute seats, people turned away, staff per session, cost, revenue, net, cost per participant, break-even fee and break-even attendance for a session-based program, with named scenarios.

    Runs with
    Python 3.10 or later
    Command
    python3 program_capacity_budget.py < input.json

    Code moduleMIT12 files, 59.8 KBruns commands

  7. Requirements traceability matrix and coverage gaps

    requirements_traceability

    Build a matrix linking requirements to design elements and tests, give each requirement a test status, and list requirements without design, tests or a pass, and links to nothing.

    Runs with
    Python 3.10 or later
    Command
    python3 requirements_traceability.py < input.json

    Code moduleMIT12 files, 58.4 KBreads files, runs commands

Give your agent these components

Your harness downloads them through Baltor with Pro, $49 a month. Cancel any time from your account page.

Get started

Compare the plansSet up your harness

More from Deterministic skills

  • Statistics for comparing resultsCompare two models, two prompts or two harness setups with statistics that hold up: calibration, conformal intervals, confidence sequences, covariance shrinkage and kernel two-sample tests.
  • Checks for agent workGive each unit of agent work one typed outcome, count the independent evidence behind a claim, and compare candidates only on the rows they all completed.
  • Calculators for public statisticsRates, ratios and indices from published definitions, with their confidence bounds and the denominators written out.
  • Algorithms that show their workAlgorithms that report each step: principal components without NumPy, sorting and union-find traces, rule based inference closures, collision clearance and resumable render plans.
  • Geometry and mesh algorithmsPure Python geometry whose glTF output loads in Godot: triangulation, convex hulls, polyline simplification, polygon offsets, subdivision, curves and gears.
  • Harness toolsTools your coding agent can call.
  • Corner casesThe inputs that break code, ready to test.
  • Stop starting from nothingFor a developer whose coding agent starts every task from nothing: give each step the guidance and reusable code it needs.
  • More efficient operationGive each step only the context, files and tools it asks for, reuse code that already exists, and measure the effect on your own task.
  • Harness FilesSkills, instruction files, tools, hooks and settings your harness picks up: what they are, how a harness gets them, and the setup for each harness.
  • GalleryBrowse Baltor's original Godot shaders, procedural textures, meshes and Blender tools, each with the render its engine check recorded.
  • Pi and Gemma 4 on Ollama CloudPi with Gemma 4 31B on Ollama Cloud searched the library, installed a skill, and a new Pi session loaded and used it.