agentleFS
guerrilla2799guerrilla2799/event-and-scale-os/skills/event-budget/SKILL.md

event-budget

Skill2 starsChanged 3 months agoMITView on GitHub

Use when the user says "what will this event cost", "build the event budget", "we came in over budget", "per head cost", "can we afford this", "cost per meeting". Builds the fully loaded cost model including the lines teams forget, computes all-in per head for hosted events, and tracks cost per qualified meeting against alternatives. Writes workspace/events/<event>/budget.md.

2 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Before committing to any event

    line 12
  2. Distinctive:

    Every line, including the ones nobody counts:

    line 24
  3. Distinctive:

    Follow-up time is budgeted: Every time

    line 98

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Event Budget

Model the real cost before committing, then track against it. Event budgets are missed for the same three reasons every time: staff time is not counted, service charges are not modeled, and follow-up is not budgeted at all.

When to use

  • Before committing to any event
  • Comparing venues, formats, or sponsorship tiers
  • Mid-planning, when scope is creeping
  • Post-event, computing cost per qualified meeting for the portfolio view

Inputs

  • Reads: workspace/events/<event>/decision.md, workspace/events/<event>/contract.md, workspace/program/charter.md
  • Needs from user: quotes where they exist, team size and loaded day rate, travel assumptions, and what is already committed

Workflow

1. Build the fully loaded model

Every line, including the ones nobody counts:

CategoryLineCommonly forgotten
AccessSponsorship or ticket cost
Additional passes beyond the included allocationYes
Venue (hosted)Room hire or minimum spend
Food and beverage per head
Beverage package, per person per hourYes
Reception in a separate spaceYes
Service charge or gratuityYes, and it is large
Coordination or administration feeYes
Tax on all of the aboveYes
Overtime if the room runs longYes
ProductionStand, banner, table throw, monitor
Printed collateral
Signage and branding
AV rental beyond what is suppliedYes
LogisticsShipping out and returnYes
Insurance certificate, if a policy change is neededYes
Storage, drayage, or handling feesYes
PeopleTravel and accommodation
Staff days at loaded costYes, and it is usually the second largest line
Executive time, costed separatelyYes
GuestsComped hotel rooms if offeredYes
Gifting, packaging, and shipping as three linesYes
PhotographerYes
DemandInvite promotion or paid amplification
List building and enrichmentYes
AfterFollow-up timeYes, almost universally
Content production from the eventYes

2. Compute all-in per head for hosted events

The menu price is roughly two-thirds of the real price. Stack it properly:

Menu per head
+ beverage package (per person per hour x contracted hours)
+ reception cost per head, if arrival is in a separate space
= subtotal
+ service charge / gratuity (%)
+ coordination or administration fee (%)
+ tax (%)
= ALL-IN PER HEAD

Compare candidate venues on the all-in number only. The ranking by menu price is frequently not the ranking by final cost, and a cheaper menu at a venue with heavy add-ons routinely loses.

3. Model against the meeting target

The number the portfolio is judged on:

Fully loaded cost / target qualified meetings = budgeted cost per qualified meeting

Compare it to what a meeting costs from outbound, and to the same number from other formats in the portfolio. This comparison is what ends bad sponsorship habits, because it is much harder to argue with than a feeling about the event.

4. Build the lean version at the same time

Decide now, while it is unemotional, what ships if the budget is cut or the date slips: which formats, which concepts, which production items. That decision is far harder to make in the week of the event.

Also note where a surplus goes if diligence reveals a cheaper reality. A stand that turns out to need a banner rather than a build frees real money, and the default should be to move it toward guest experience or gifting rather than to expand the stand.

5. Set the tracking cadence

Weekly against committed and spent, from T-8 onward. Flag every variance over 10% at the time rather than at the end.

6. Reconcile after the event

Actual against budget, line by line, with a note on every variance. This is what makes next year's model accurate, and it takes twenty minutes if you do it in the week after.

Output

  • Writes: workspace/events/<event>/budget.md from templates/event-budget-model.csv
  • Prints: the fully loaded total, all-in per head where relevant, budgeted cost per qualified meeting with the comparison, the lean version, and the lines with the least certainty

Rules & quality bar

  • Staff days are in the model. Loaded cost, including travel days
  • Follow-up time is budgeted. Every time
  • All-in per head, never menu price, for any hosted event
  • Cost per qualified meeting is computed at budget time, not just afterward
  • The lean version is decided before it is needed
  • No quotes invented. Estimated lines are labeled as estimates with the basis stated
  • Every variance over 10% is flagged when it happens

Related skills

  • Reads: event-selection, sponsorship-negotiation, venue-selection
  • Feeds: event-measurement (the cost side of every scorecard)
  • See also: docs/operations-runbook.md section 5 for what stacks on a venue bill

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.