Install
$ agentstack add skill-brenbuilds1-cutweight-weigh-in ✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
About
Weigh-In
The scale for your agent. skill-diet finds what to cut; weigh-in tells you what you weigh, before the cut and after it. Step on the scale first, cut, step on it again.
Method
- Measure the always-on bill exactly as skill-diet does: installed skills
(frontmatter name plus description each), memory files loaded at session start (CLAUDE.md, AGENTS.md, local variants, imports), MCP tool schemas (eager-loaded only; a server you cannot enumerate is unknown, never zero).
- Rough tokens for English markdown: characters / 3 on Claude models with
the Opus 4.7 tokenizer (Opus 4.7+, Sonnet 5, Fable 5), characters / 3.5 to 4 on older Claude and GPT-style tokenizers. Label estimates.
- Read the last card from
.cutweight/weigh-ins.mdif it exists. Compute
the delta.
- Print the card. Append it to the log. Never edit old cards.
Weight Classes
Cutweight's own scale, by always-on tokens per message:
| class | always-on | |---|---| | flyweight | under 1,000 | | lightweight | under 3,000 | | middleweight | under 8,000 | | heavyweight | under 20,000 | | superheavyweight | 20,000 and up |
The Card
cutweight weigh-in: 2026-07-10
always-on: 7,412 tokens on every message
skills: 3,509 (27 installed)
memory files: 3,903
mcp schemas: ~0 (deferred loading)
class: middleweight
last weigh-in: 9,180 (-19%, was heavyweight)
next cut: the 25-skill plugin billing 2,462 for 4 skills used
Keep the card under 12 lines. It is made to be posted.
Hard Rules
- The log is append-only. A rewritten history is not a weigh-in.
- Measured or labeled-estimate numbers only.
- The card always names the single next cut, or says "at weight" if lean.
- Never name an agent-maintained memory file (auto-memory index, session
memory) as the next cut. Bill it on the card, flag it to its owner. Its lines are the agent's retrieval keys; hand-trimming them breaks recall.
- A card meant for posting shows counts and categories, never private tool,
server, or plugin names. Generalize anything internal before it leaves the machine.
- Keep
.cutweight/out of version control; the log stays on the machine. - Weigh-in changes nothing but its own log. The human does the cutting.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: brenbuilds1
- Source: brenbuilds1/cutweight
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet — be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.