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 agentmods add skills/udecode/plate-template/hard-cutnpx skills add udecode/plate-template --skill hard-cutgit clone --depth 1 https://github.com/udecode/plate-templateWrote 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/udecode/plate-template/hard-cut)<a href="https://agentmods.dev/skills/udecode/plate-template/hard-cut"><img src="https://agentmods.dev/badge/skills/udecode/plate-template/hard-cut.svg" alt="Measured on agentmods" 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 | $0.00067 | $0.00415 |
| Opus 5 | $0.00034 | $0.00208 |
| Sonnet 5 | $0.00013 | $0.00083 |
| Haiku 4.5 | $0.00007 | $0.00042 |
Grade A, and why
hard-cut 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 3d 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.
This is a copy
100% identical to hard-cut — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
Hard Cut
Use this when a feature should die, not linger.
Rules
- Delete the surface. Do not deprecate it.
- Do not leave
throw new Error("Not implemented"), placeholder notices, "feature removed" banners, or TODOs about bringing it back unless the user explicitly asks. - Do not keep compatibility aliases, deprecated shims, fallback parsing, migration bridges, or dead exports.
- Delete tests for deleted behavior. Keep tests only for the behavior that still exists.
- Delete comments that describe deleted code or mourn the old feature.
- If removal exposes adjacent dead code, keep cutting until the graph is clean.
Sweep
- Find the real surface area:
- exports
- commands and flags
- routes
- UI entrypoints
- feature flags
- docs and examples
- Trace references with
rg. - Delete the implementation and the glue:
- call sites
- types
- state
- tests
- docs
- comments
- Grep again for the removed name and obvious aliases.
- Run the narrowest honest verification for the surviving product.
Smells
- deprecated notices
- not-implemented throws
- stub handlers
- dead enum or union members
- permanently-false feature-flag branches
- unused env vars and config
- tests that only prove the deleted feature used to exist
Bias
If the choice is between deleting more code and leaving a zombie seam, delete more code.
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.
- 3d ago First seen · 60 lines · 67 tokens per session scan A 83081a0c4139
hard-cut is a skill published in the GitHub repository udecode/plate-template (59 stars, last pushed 2mo ago), licensed MIT. It adds 67 tokens to every session and 415 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to hard-cut, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
autogoal
Create, verify, repair, and close durable Codex goals with measurable outcomes, evidence gates, plan templates, blocker handling, completion audits, and goal-backed workflow repair.
components
React component architecture for creating composable, accessible components with data attributes. Use when creating/updating composable components, not for higher-level feature/page components.
react
React patterns with destructured props, compiler optimization, Effects, and Tailwind v4 syntax. ALWAYS use when using React.
autoreview
Pre-commit/ship code review: Codex default; optional Claude, Pi, Droid, Copilot, Cursor, or OpenCode.
resolve-pr-feedback
Resolve GitHub PR review feedback with source-backed triage, fixes, autogoal plan state, mandatory autoreview closeout, replies, and thread resolution.
tdd
Test-driven development with red-green-refactor loop. Use when user wants to build features or fix bugs using TDD, mentions "red-green-refactor", wants integration tests, or asks for test-first development.