SavigeSystemZ/concise-communication
.cursor/skills/concise-communication/SKILL.md
Opt-in ultra-concise assistant replies to reduce OUTPUT tokens (Caveman-style). Use when the user asks for caveman, token-efficient, terse, or compressed answers; or for long/cost-sensitive sessions. NOT default—never use for handoffs, legal/safety text, or verbatim user requirements.
testing
Updated Apr 16, 2026
$ install --global
skillsauthnpx skillsauth add SavigeSystemZ/Orignym concise-communicationInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 16, 2026, 5:19 PM140.6s1 file scanned
SKILL.md
- name:
- concise-communication
- description:
- Opt-in ultra-concise assistant replies to reduce OUTPUT tokens (Caveman-style). Use when the user asks for caveman, token-efficient, terse, or compressed answers; or for long/cost-sensitive sessions. NOT default—never use for handoffs, legal/safety text, or verbatim user requirements.
Concise communication (token-efficient output)
Purpose
Compress assistant output (not user instructions): drop filler, hedging, and redundant prose while keeping full technical accuracy. Pattern aligns with the community Caveman skill (JuliusBrussee/caveman, MIT); this repo ships a host-neutral Cursor skill so any agent that reads .cursor/skills/ can apply the same rules.
Important: Savings apply mainly to output tokens. Input context (repo, rules, large files) usually dominates cost—pair with _system/CONTEXT_BUDGET_STRATEGY.md and tiered loading for input-side efficiency.
When to activate (explicit user intent)
- User says: caveman, concise, terse, token-efficient, fewer tokens, no fluff, bullet-only, etc.
- User runs command
/concise-session(see.cursor/commands/concise-session.md). - Long or budget-sensitive sessions after the user opts in.
When NOT to use (override concise mode)
- Handoff / continuity:
WHERE_LEFT_OFF.md,HANDOFF_PROTOCOL.md, checkpoint packets—must stay complete and unambiguous. - User instructions: reproduce requirements verbatim when ambiguity would change behavior; do not “compress away” constraints.
- Security, compliance, legal, accessibility: prefer clarity over brevity; do not omit warnings or steps.
- Exact quotes: error messages, logs, file paths, commands, API signatures—copy verbatim.
- Git commits / PRs / release notes: use normal professional tone unless the user explicitly wants terse style there too.
Intensity levels
| Level | Behavior | |-------|----------| | lite | Remove filler; keep full sentences and grammar. | | full (default) | Short sentences; fragments OK; strip articles where safe; no pleasantries. | | ultra | Telegraphic; minimal connective words; only for expert readers and non-handoff work. |
If the user does not specify, use full.
Rules (always)
- Preserve code blocks, inline code, paths, URLs, numbers/versions, commands, and quoted tool output exactly.
- Do not shorten or paraphrase user requirements or acceptance criteria.
- Do not skip validation steps or safety checks to save words—state them compactly instead.
- Stop when the answer is complete; do not add engagement filler.
Deactivate
- User says: normal mode, stop concise, verbose, full sentences, etc.
Related
_system/CONTEXT_BUDGET_STRATEGY.md— input-side tiering._system/CONTEXT_INDEX.md— find other workflows.- Upstream optional install:
npx skills add JuliusBrussee/caveman(Claude Code/Codex plugins; separate from this repo skill).
Related Skills
SavigeSystemZ/verify-gate
testing
VerifiedTrustedCommunity
Run verification before push, checkpoint, or claiming completion.
SKILL.mdUpdated Apr 16, 2026
SavigeSystemZ/release-readiness
testing
VerifiedTrustedCommunity
Evaluate whether work is truly ready for checkpoint, milestone completion, or release claims.
SKILL.mdUpdated Apr 16, 2026
SavigeSystemZ/prompt-pack-generator
documentation
VerifiedTrustedCommunity
Generate milestone prompt packs grounded in the repo's canonical docs.
SKILL.mdUpdated Apr 16, 2026
SavigeSystemZ/performance-review
testing
VerifiedTrustedCommunity
Audit changes for performance budget compliance and optimization opportunities
SKILL.mdUpdated Apr 16, 2026