Dwi budget
A modular human layer that helps reduce overplanning, token waste, context loss, and actions taken without clear permission.
npx -y skills add thienhoc/dwi-by-thienhoc --skill dwi-budgetAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- 13 days oldThe repository was created 13 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
- 2 stars2 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Set and report practical token, context, time, tool-call, and coordination boundaries for coding-agent work. Use when resource use is unclear or needs a checkpoint. Do not invent measurements, monetary savings, cache benefit, or precision that the harness does not expose.
SKILL.md
2.6 KB, as published. Nobody here has run it
Dwi Budget
Make resource boundaries visible without turning them into performance theater.
Establish the boundary
Before substantial work, name the smallest useful budget the task needs:
- outcome boundary;
- context boundary;
- tool-call or stage boundary when relevant;
- time or checkpoint boundary when available;
- evidence required before spending more.
Do not ask for a numeric budget when a simple scope boundary is clearer.
Measurement labels
Report only fields supported by current evidence:
| Field | Meaning |
|---|---|
| Gross input | All input tokens reported by the harness |
| Cached input | Input tokens explicitly reported as cache reads |
| New input | Gross input minus cached input, only when both are comparable |
| Output | Output tokens reported by the harness |
| Wall time | Elapsed time measured for the stated scope |
| Tool calls | Calls counted in the stated stage or task |
| Coordination | Time, calls, or stages spent handing work across agents |
If a field is unavailable, mark it UNKNOWN or UNAVAILABLE. Do not estimate it silently.
Cache and cost rules
- Cached input is reuse evidence, not automatically a monetary saving.
- A percentage needs a denominator and scope.
- Token counts from different providers or tools may not be comparable.
- Price changes over time; use a dated price source before calculating money.
- Do not convert one canary into a universal claim.
Spending protocol
- Use the cheapest evidence that can answer the current question.
- Reuse already-read context instead of repeatedly loading it.
- Prefer bounded queries over broad repository scans.
- Add a second agent only when independent perspective or disjoint work has a defined value.
- Checkpoint before crossing the stated boundary.
- Ask for more budget only with the new uncertainty and expected value.
Report format
Use:
Outcome: <what was achieved>
Boundary: <scope or budget used>
Observed: <supported measurements>
Unknown: <unavailable measurements>
Next spend: <none, or one justified step>
Stop condition
Stop spending when the outcome and required evidence are complete, or when the next unit of work lacks a clear expected value. Near exhaustion, preserve a concise checkpoint rather than compressing uncertainty into a success claim.