eco
Skill69 starsChanged 7 months agoMITView on GitHub
Run one sc4sap skill in eco cost mode (cheaper sub-agent models and effort, lower main-thread effort; same deliverable as standard) without changing preferences — `/sc4sap:eco <skill> <args>`. Also re-applies low effort on continuation turns of an eco run (`--attach`).
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 0 are distinctive, and 4 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 14
Every response triggered by this skill MUST begin with [Model: <main-model> · Dispatched: <sub-summary> · Mode: eco] per …
- Very specific: line 25
If the arguments contain --standard → say that eco and standard conflict, and stop.
- Very specific: line 26
If the target has no eco variant (setup, sap-option, sap-doctor, mcp-setup, trust-session, eco, and every skill listed as "No eco variant" …
- Very specific: line 27
If the target is unknown or missing → list the skills that have an eco recipe (common/cost-mode.md § lever C) and stop.
≈ “Common” is an estimate: at least 1 in 5 of the 308,232 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
SC4SAP Eco
One-off entry point for eco cost mode — same deliverable as standard, cheaper models and effort. Rules: ../../common/cost-mode.md. This skill's effort: low frontmatter lowers the main-thread effort while it is active — that is lever B of the cost mode. The effect ends at the next user turn, so eco runs re-enter here with --attach.
<Response_Prefix>
Every response triggered by this skill MUST begin with [Model: <main-model> · Dispatched: <sub-summary> · Mode: eco] per ../../common/model-routing-rule.md § Response Prefix Convention — except in --attach mode, which emits nothing.
</Response_Prefix>
<Modes>--attach
Called by a skill already running in eco (first action of the run when eco came from preferences / --eco, and first action of every continuation turn). Do nothing else: no output, no file reads. Return control to the calling skill and continue its work in this same turn.
<skill> <args> (user-facing)
- If the arguments contain
--standard→ say that eco and standard conflict, and stop. Parse the first token as the target skill. Acceptcreate-program,/sc4sap:create-program,sc4sap:create-program. Normalize to the bare name. - If the target has no eco variant (
setup,sap-option,sap-doctor,mcp-setup,trust-session,eco, and every skill listed as "No eco variant" incommon/cost-mode.md§ lever C) → say so in one line and stop. Do not run it. - If the target is unknown or missing → list the skills that have an eco recipe (
common/cost-mode.md§ lever C) and stop. - Invoke
Skill("sc4sap:<target>", "<args> --eco --via-eco"). The target resolves--ecofirst and skips its first--attachbecause of--via-eco(cost-mode § Resolution), so preferences are not read for the mode and not changed. - The target skill owns the run from here: its own prefix (with
· Mode: eco), banners, questions, and report.
</Modes><Examples>
- `/sc4sap:eco compare-programs ZSDR_SALES_KR ZSDR_SALES_EU` → the same report (all dimensions, English companion), scouts on Haiku, analyst and writer on Sonnet · low.
- `/sc4sap:eco program-to-manual ZMMR_PO_STATUS` → the same manual (all scenarios, English companion), written on Sonnet · low.
- `/sc4sap:eco package-to-process ZSD300 lang=ko` → the same documents, Haiku scouts read every source, Sonnet · low analyst and writer.
- To make eco the default instead: `/sc4sap:sap-option cost mode`.
</Examples>Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- rozputnii/ai-usage-app★ 0same 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 repository23 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- analyze-cbo-objSkill
- analyze-codeSkill
- analyze-symptomSkill
- ask-consultantSkill
- compare-programsSkill
- config-to-documentSkill
- create-objectSkill
- create-programSkill
- interface-mapping-specSkill
- mcp-setupSkill
- module-to-processSkill
- package-to-processSkill
- program-to-manualSkill
- program-to-specSkill
- project-dashboardSkill
- role-matrixSkill
- sap-doctorSkill
- sap-optionSkill
- setupSkill
- smartform-from-pdfSkill
- smartform-previewSkill
- trust-sessionSkill
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
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.