conscious-spending
Skill1 starsChanged 7 months agoMITView on GitHub
Monthly Conscious Spending Plan check-in (Ramit Sethi). Lighter-weight than money-date. Reviews whether actual spending matched intentional categories this month, flags drifts.
In this repository34 other files it gives its agents.
- accountability-mirrorSkill
- annual-physicalSkill
- bills-and-subsSkill
- brotherhoodSkill
- date-nightSkill
- decision-journalSkill
- discomfort-doseSkill
- emotion-coachSkill
- enough-checkSkill
- errand-batchSkill
- evening-examenSkill
- father-reviewSkill
- friend-reach-outSkill
- gratitudeSkill
- hard-conversationSkill
- home-maintenanceSkill
- kid-oneononeSkill
- love-map-refreshSkill
- mentor-touchSkill
- money-dateSkill
- morning-resetSkill
- parent-checkinSkill
- partner-checkinSkill
- partner-reviewSkill
- repairSkill
- resetSkill
- screwupSkill
- shutdown-ritualSkill
- sleep-protocolSkill
- training-planSkill
- values-checkSkill
- virtue-reviewSkill
- weekly-reviewSkill
- weekly-serviceSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
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
- Distinctive: line 39
If you dialed DOWN on something (restaurants, clothes, whatever), did this month's spending reflect that, or did the habit win?
- Distinctive: line 60
If any are behind, either adjust the monthly contribution or adjust the goal.
- Distinctive: line 103
No month will be perfectly on target.
- Distinctive: line 109
If yes on all three, the system is working.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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.
Files
/conscious-spending
Monthly check-in against the Conscious Spending Plan defined in /money-date. Faster. 15-20 minutes.
Step 1: Pull the month
From whatever budgeting tool the user uses (Monarch, YNAB, Copilot, Mint replacement, bank categories):
- Total income this month.
- Total spending by bucket (Fixed, Invest, Save, Guilt-free).
- Any categories that jumped vs. last 3-month average.
Step 2: Bucket check
Compare actuals to targets:
| Bucket | Target | Actual | Flag |
| Fixed | 50-60% | <%> | |
| Invest | 10%+ | <%> | |
| Save | 5-10% | <%> | |
| Guilt-free | 20-35% | <%> |
For each bucket that is off target, ask one question:
- Over-target? Was this a one-off (big vet bill, surprise fix, gift) or a drift?
- Under-target on invest/save? Did automation fire? If not, why not?
Step 3: Money dial check
The money dials from the last money date — were they honored?
Example: if you dialed UP on "travel with family" this quarter, did any of this month's spending reflect that? A trip planned, a flight booked, a weekend away?
If you dialed DOWN on something (restaurants, clothes, whatever), did this month's spending reflect that, or did the habit win?
The dials are a promise to yourself. This is the accountability check.
Step 4: Anomaly scan
Flag anything:
- One-time charges over a threshold (set by user).
- Subscriptions that should have been caught (run
/bills-and-subsif more than one zombie shows). - Categories 50%+ above baseline (groceries, gas, whatever).
- A new recurring charge you don't recognize.
Step 5: Sinking funds
Are the sinking funds on track?
- Vacation fund: still projected to hit goal by target date?
- Tax fund: on track for April?
- Car fund (replacement or repair)?
- Gift fund (for the holidays)?
If any are behind, either adjust the monthly contribution or adjust the goal.
Step 6: One adjustment for next month
Pick ONE thing to change next month:
- Move $X/month more into investments.
- Cap guilt-free at $Y.
- Freeze a specific category for the month.
- Set up a new sinking fund.
One. Not a portfolio of heroic fixes. One change, tracked.
Output
Append to ~/adulting-data/journal/spending-log.md:
# Spending review — <month, year>
## Actuals vs. targets
Fixed: <%> (target 50-60%) <flag>
Invest: <%> (target 10%+) <flag>
Save: <%> (target 5-10%) <flag>
Guilt-free: <%> (target 20-35%) <flag>
## Dials honored?
Up: <categories and whether spending matched>
Down: <categories and whether spending matched>
## Anomalies
- <item>
## Sinking funds
- Vacation: <status>
- Taxes: <status>
- <other>: <status>
## Adjustment for next month
<one thing>The month-to-month reality
No month will be perfectly on target. That is fine. The goal is a trend:
- Over 6 months, is the invest bucket trending up?
- Over 6 months, is guilt-free trending toward your actual values?
- Over 6 months, is net worth growing?
If yes on all three, the system is working. Adjust the small stuff, not the big stuff.
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
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.

