cost-review
Skill0 starsChanged 3 months agoMITView on GitHub
Review a design or a running system for cost. Use before committing to an architecture, when a bill jumps, or during quarterly optimisation.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- DataWithBaraa/claude-code-data-engineering-skillstheir own version, first seen Nov 1, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- DataWithBaraa/claude-code-data-engineering-skills★ 84same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository16 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .claude/commands/agents.mdAGENTS.md
- .opencode/AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .github/copilot-instructions.mdCopilot instructions
- .cursor/rules/caveman.mdcCursor rule
- adrSkill
- agent-registrySkill
- data-contractSkill
- delegation-protocolSkill
- marketplaceSkill
- onboardingSkill
- orchestrationSkill
- postmortemSkill
- runbookSkill
- threat-modelSkill
The file
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 5 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
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 58
Every row: a number, a mechanism, an honest risk.
- Distinctive: line 75
No recommendation without a measured saving.
- Distinctive: line 76
Never trade away a reliability guarantee without saying so explicitly and loudly.
- Distinctive: line 77
Verify in the following billing period.
- Distinctive: line 79
Check for a hard limit before downsizing anything — quotas, connection pools, licences.
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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
Cost Review
Procedure
- Attribute. Break spend by team, service, and environment. Untagged spend is finding number one — you cannot optimise what you cannot attribute.
Find the drivers. Rank by absolute spend, then look for the usual suspects:
Driver Typical cause Cross-zone / egress traffic Chatty services split across zones; no locality awareness Storage class Everything on hot storage forever; no lifecycle policy Idle capacity Non-production running nights and weekends Over-provisioning Sized for a peak that never arrived, never revisited Managed service premium Paying for an operator you do not need at this scale Log and metric volume Debug logging left on; high-cardinality labels LLM tokens No caching, oversized model for the task, unbounded context - Compute unit economics. Cost per request, per tenant, per model call. Totals hide everything — a bill that doubled while traffic tripled is a win.
- Model at scale. What does this cost at 10x? A design that is cheap today and ruinous at scale is rejected now, while changing it is still cheap.
- Recommend with numbers. Each item: measured monthly saving, effort, and the performance or reliability risk it introduces.
Output
| Finding | Monthly cost | Proposed change | Saving | Risk | Effort |
Worked example
Weak — unactionable, and quietly dangerous:
- NAT Gateway costs are high, consider reducing traffic.
- Instances look oversized, recommend downsizing.
- Consider reserved instances for savings.Nobody can act on these, and "downsize" with no risk statement is how a cost review causes an outage.
Strong:
| Finding | Monthly | Change | Saving | Risk | Effort |
| NAT Gateway data processing: 41 TB/mo. 78% is S3 traffic routed through NAT. | $4,920 | Add S3 Gateway VPC endpoint | $3,840 (verified: gateway endpoints are free, traffic bypasses NAT) | None. Route table change, reversible in minutes. | 1h |
| 14 non-prod RDS instances running 24/7 | $6,200 | Stop 19:00–07:00 and weekends via scheduler | $4,100 (66% of hours) | Overnight CI jobs on 2 of the 14 — exclude those. | 4h |
api service: p99 CPU 12%, sized m5.4xlarge × 9 | $3,740 | → m5.xlarge × 9, keep replica count | $2,800 | Real. 4x less burst headroom. Verified against the last Black Friday peak: 34% CPU at 4.1x normal traffic. Still 3x headroom after the change. Requires a load test before rollout. | 1d + load test |
CloudWatch: 2.1 TB logs/mo, 61% is DEBUG from one service | $1,480 | Set that service to INFO; 7-day retention on debug streams | $900 | Lose debug detail on that service; it has tracing, so diagnosis is unaffected. | 2h |
| Total | $11,640/mo |
Every row: a number, a mechanism, an honest risk. The third row is the important one — it is the biggest behavioural change and it names the load test as a precondition instead of pretending the risk is zero.
Anti-patterns
| Anti-pattern | Why it fails |
| Recommendation with no measured saving | Unprioritisable. The 5% item gets done, the 40% item does not. |
| Trading reliability for cost silently | The outage costs more than the year of savings |
| Optimising the total instead of the unit cost | Punishes growth; rewards shrinking the business |
| Reserved commitments without utilisation data | Locks in today's mistake for one to three years |
| Findings sent to finance | Finance cannot change a route table. Send to the owning team. |
| Savings never verified | Half of claimed savings do not appear on the next bill |
Rules
- No recommendation without a measured saving. Estimates are labelled as estimates.
- Never trade away a reliability guarantee without saying so explicitly and loudly.
- Verify in the following billing period. Unverified savings do not count.
- Route findings to the team that can act, not to finance.
- Check for a hard limit before downsizing anything — quotas, connection pools, licences.
Done when
- Attribution coverage stated; untagged spend quantified.
- Findings ranked by absolute saving, not by ease.
- Every row has a saving, a risk, and an effort estimate.
- Unit economics reported alongside totals.
- Cost at 10x scale modelled for design reviews.
- A verification date is set for the following billing period.
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.

