Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add brenbuilds1/cutweight --skill cutweight-weighgit clone --depth 1 https://github.com/brenbuilds1/cutweightWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/brenbuilds1/cutweight/cutweight-weigh)<a href="https://agentmods.dev/skills/brenbuilds1/cutweight/cutweight-weigh"><img src="https://agentmods.dev/badge/skills/brenbuilds1/cutweight/cutweight-weigh/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/brenbuilds1/cutweight/cutweight-weigh"><img src="https://agentmods.dev/badge/skills/brenbuilds1/cutweight/cutweight-weigh.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00093 | $0.00717 |
| Opus 5.5 | $0.00037 | $0.00287 |
| Sonnet 5.5 | $0.00019 | $0.00143 |
| Haiku 4.5 | $0.00009 | $0.00072 |
Grade A, and why
cutweight-weigh scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 23d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Weigh-In
The scale for your agent. cutweight-diet finds what to cut; cutweight-weigh 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 cutweight-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.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 23d ago First seen · 71 lines · 93 tokens per session scan A a65bb1a5e1da
cutweight-weigh is a skill published in the GitHub repository brenbuilds1/cutweight (3 stars, last pushed 10d ago), licensed MIT. It adds 93 tokens to every session and 717 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-23.
Other skills, from other repositories
sdd
Execute the Liatrio Spec-Driven Development (SDD) workflow when explicitly invoked by the user. NOTE: this skill is NOT intended to be dynamically loaded or automatically triggered; it should only ever be explicitly called by the user.
prp-manager
Plan and implement features with PRPs (Product Requirements Prompts), implementation blueprints that give an AI coding agent the requirements, codebase context and validation steps to build a feature in one pass. Use this skill when the user wants to plan, spec or scope a feature before coding it, asks for an…
compiling-project-guidelines
Compile scattered guideline sources into one scope-aware COMPILED-GUIDELINES.md for other skills and ult-context-generate's Constraints layer. Do NOT use to enforce rules at runtime.
cep-wizard
Launch a local, localhost-only browser wizard with two journeys — layout onboarding for a project with ult-repo-layout installed, initialized or not — guides an uninitialized or not-yet-discovered repo through Run Discover, then shows resolved layer/slot state through four labeled boxes and a directory picker, and…
codegraph
Generate a codebase knowledge graph with graphify at graphify-out/ so other skills can query cross-file relationships before touching code. Do NOT use for runtime profiling.
institutional-memory-distill
Distill decisions, reasoning, and rejected alternatives from PRs, design docs, and postmortems into the project's decisionledger, so ult-context-generate's trip-wire can surface institutional memory before new work quietly repeats settled ground. Do NOT use to query the ledger against new work or decide…