zsp/everything-claude-code
1
0
Fork 0
mirror of https://github.com/affaan-m/everything-claude-code.git synced 2026-03-30 13:43:26 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix(skills): tighten token-budget-advisor triggers

Browse Source
This commit is contained in:
Affaan Mustafa
2026-03-29 00:19:10 -04:00
parent ab49c9adf5
commit e50e64ac05
2 changed files with 10 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
README.md
View File

@@ -295,7 +295,7 @@ everything-claude-code/
| |-- plugin.json # Plugin metadata and component paths | |-- plugin.json # Plugin metadata and component paths
| |-- marketplace.json # Marketplace catalog for /plugin marketplace add | |-- marketplace.json # Marketplace catalog for /plugin marketplace add
| |
|-- agents/ # 29 specialized subagents for delegation |-- agents/ # 30 specialized subagents for delegation
| |-- planner.md # Feature implementation planning | |-- planner.md # Feature implementation planning
| |-- architect.md # System design decisions | |-- architect.md # System design decisions
| |-- tdd-guide.md # Test-driven development | |-- tdd-guide.md # Test-driven development

16
skills/token-budget-advisor/SKILL.md
View File

@@ -10,11 +10,12 @@ description: >-
"short answer", "detailed answer", "full answer", "short answer", "detailed answer", "full answer",
"respuesta corta vs larga", "cuántos tokens", "ahorrar tokens", "respuesta corta vs larga", "cuántos tokens", "ahorrar tokens",
"responde al 50%", "dame la versión corta", "quiero controlar cuánto usas", "responde al 50%", "dame la versión corta", "quiero controlar cuánto usas",
"75%", "100%", "at 25%", "at 50%", "at 75%", "at 100%", "25% depth", "50% depth", "75% depth", "100% depth",
"give me the full answer", or any variant where the user wants "give me the full answer", or any variant where the user wants
to control length, depth, or token usage — even without mentioning tokens. to control length, depth, or token usage — even without mentioning tokens.
DO NOT TRIGGER when: user has already specified a level in the current DO NOT TRIGGER when: user has already specified a level in the current
session (maintain it) or the request is clearly a one-word answer. session (maintain it), the request is clearly a one-word answer, or
"token" refers to auth/session/payment tokens rather than response size.
origin: community origin: community
--- ---
@@ -72,7 +73,7 @@ Choose your depth level:
[3] Detailed (75%) -> ~[tokens] Full answer with alternatives [3] Detailed (75%) -> ~[tokens] Full answer with alternatives
[4] Exhaustive (100%) -> ~[tokens] Everything, no limits [4] Exhaustive (100%) -> ~[tokens] Everything, no limits
Which level? (1-4 or say "25%", "50%", "75%", "100%") Which level? (1-4 or say "25% depth", "50% depth", "75% depth", "100% depth")
Precision: heuristic estimate ~85-90% accuracy (±15%). Precision: heuristic estimate ~85-90% accuracy (±15%).
``` ```
@@ -98,10 +99,10 @@ If the user already signals a level, respond at that level immediately without a
| What they say | Level | | What they say | Level |
|----------------------------------------------------|-------| |----------------------------------------------------|-------|
| "1" / "25%" / "short answer" / "brief" / "tldr" / "one-liner" | 25% | | "1" / "25% depth" / "short answer" / "brief answer" / "tldr" | 25% |
| "2" / "50%" / "moderate detail" / "balanced answer" | 50% | | "2" / "50% depth" / "moderate detail" / "balanced answer" | 50% |
| "3" / "75%" / "detailed answer" / "thorough explanation" | 75% | | "3" / "75% depth" / "detailed answer" / "thorough explanation" | 75% |
| "4" / "100%" / "exhaustive" / "everything" / "full answer" | 100% | | "4" / "100% depth" / "exhaustive answer" / "full deep dive" | 100% |
If the user set a level earlier in the session, **maintain it silently** for subsequent responses unless they change it. If the user set a level earlier in the session, **maintain it silently** for subsequent responses unless they change it.
@@ -124,6 +125,7 @@ This skill uses heuristic estimation — no real tokenizer. Accuracy ~85-90%, va
- "Explain OAuth token refresh flow." (`token` here is domain language, not a budget request) - "Explain OAuth token refresh flow." (`token` here is domain language, not a budget request)
- "Why is this JWT token invalid?" (security/domain usage, not response sizing) - "Why is this JWT token invalid?" (security/domain usage, not response sizing)
- "What is 2 + 2?" (trivially short answer) - "What is 2 + 2?" (trivially short answer)
- "Complete the refactor and then open a PR." (`complete` here is task language, not a depth choice)
## Source ## Source