KurutoDenzeru/tersio
✂️ Token saver & usage tracker for coding agents: terse caveman replies, compact RTK shell output, lean Ponytail code, Headroom compression, pstack rigor, and a gain dashboard — one-command combos over one shared extension tree.
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
Copy this rig
# review before running: this installs third-party code
$ claude mcp add tersio -- tersio mcp MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.
$ claude mcp add tersio -- tersio mcp $ npx degit <redacted>-audit .claude/skills/ponytail-audit $ npx degit <redacted>-debt .claude/skills/ponytail-debt $ npx degit <redacted>-gain .claude/skills/ponytail-gain $ npx degit <redacted>-help .claude/skills/ponytail-help $ npx degit <redacted>-review .claude/skills/ponytail-review $ npx degit <redacted> .claude/skills/ponytail $ npx degit <redacted> .claude/skills/architect $ npx degit <redacted> .claude/skills/arena $ npx degit <redacted>-checklist .claude/skills/benchmark-checklist $ npx degit <redacted>-radius .claude/skills/blast-radius $ npx degit <redacted> .claude/skills/bro $ npx degit <redacted> .claude/skills/correct $ npx degit <redacted>-formal-verification-skill .claude/skills/create-formal-verification-skill $ npx degit <redacted>-verification-skill .claude/skills/create-verification-skill $ npx degit <redacted>-it-out .claude/skills/figure-it-out $ npx degit <redacted> .claude/skills/how $ npx degit <redacted>-your-own-words .claude/skills/in-your-own-words $ npx degit <redacted> .claude/skills/interrogate $ npx degit <redacted>-video .claude/skills/ketchup-video $ npx degit <redacted> .claude/skills/ketchup $ npx degit <redacted>-formal-verification-skill .claude/skills/maintain-formal-verification-skill $ npx degit <redacted>-verification-skill .claude/skills/maintain-verification-skill $ npx degit <redacted>-comments .claude/skills/no-comments $ npx degit <redacted> .claude/skills/recall $ npx degit <redacted> .claude/skills/reflect $ npx degit <redacted> .claude/skills/sharpen $ npx degit <redacted>-me-your-work .claude/skills/show-me-your-work $ npx degit <redacted> .claude/skills/statechart $ npx degit <redacted> .claude/skills/swarm $ npx degit <redacted> .claude/skills/tdd $ npx degit <redacted> .claude/skills/teach $ npx degit <redacted>-writing .claude/skills/technical-writing $ npx degit <redacted>-best-practices .claude/skills/typescript-best-practices $ npx degit <redacted> .claude/skills/unslop $ npx degit <redacted> .claude/skills/why $ npx degit <redacted> .claude/skills/caveman $ npx degit <redacted> .claude/skills/combo $ npx degit <redacted> .claude/skills/headroom $ npx degit <redacted> .claude/skills/pstack $ npx degit KurutoDenzeru/tersio/plugins/tersio/skills/rtk .claude/skills/rtk
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 16.2k rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(./.env.*)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(git push --force:*)",
"Read(**/*.pem)",
"Read(.env)",
"Read(~/.aws/**)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Bash(rm -rf *)",
"Bash(sudo *)",
"Bash(sudo:*)",
"Bash(rm -rf /)",
"Bash(git push -f:*)",
"Read(.env.*)",
"Bash(git reset --hard*)",
"Bash(rm -rf /*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(gh pr merge *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(gh pr merge:*)",
"Bash(gh pr create *)",
"Bash(git reset --hard:*)",
"Bash(npm publish:*)",
"Bash(git rebase *)"
]
}
} MCP servers (1)
| server | source | est. tokens |
|---|---|---|
| tersio | binary | 2.5k |
Skills (42)
ponytail-auditponytail-debtponytail-gainponytail-helpponytail-reviewponytailarchitectarenabenchmark-checklistblast-radiusbrocorrectcreate-formal-verification-skillcreate-verification-skillfigure-it-outhowin-your-own-wordsinterrogateketchup-videoketchupmaintain-formal-verification-skillmaintain-verification-skillno-commentsrecallreflectsharpenshow-me-your-workstatechartswarmtddteachtechnical-writingtypescript-best-practicesunslopwhycavemancomboheadroompstackrtktersio-modestersio
Similar rigs
sergchil/jutsu
poteto's pstack for Claude Code inside T3 Code: one mode that routes every task to a rigorous playbook.
Skill Collector 2.1k tok · · Q0
sean-brydon/shipstack
Rigorous agent workflows for Claude Code, built for Shipyard. A port of pstack: /shipit routes a task to a playbook and proves the work.
Skill Collector 2.0k tok · · Q0
marius-pieptea/treeboss
An agent harness and software factory: one daemon and UI for the coding CLIs you already pay for, from idea to shipped app.
Skill Collector 3.7k tok · · Q3
painhardcore/pstack
Portable coding-agent workflows adapted from Cursor’s pstack for Codex, Claude Code, and OpenCode.
Skill Collector 3.9k tok · · Q0