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 mikestangdevs/craft-skills --skill delete-thisgit clone --depth 1 https://github.com/mikestangdevs/craft-skillsWrote 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/mikestangdevs/craft-skills/delete-this)<a href="https://agentmods.dev/skills/mikestangdevs/craft-skills/delete-this"><img src="https://agentmods.dev/badge/skills/mikestangdevs/craft-skills/delete-this.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 5.1 | $0.00102 | $0.01367 |
| Opus 5 | $0.00051 | $0.00683 |
| Sonnet 5 | $0.00020 | $0.00273 |
| Haiku 4.5 | $0.00010 | $0.00137 |
Grade A, and why
delete-this 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 7d 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Delete This
The failure mode this fixes
Codebases accrete. Every feature adds; almost nothing subtracts. Agents make this worse — they're trained to produce code, not remove it, so they route around dead code instead of deleting it. The result is a graveyard of commented-out blocks, flags that are always true, abstractions invented for a second caller that never arrived, and TODOs from engineers who left two years ago. Every line of it is read, parsed, and feared by everyone who touches the file.
The best refactor is often a deletion. This skill finds what no longer earns its place and removes it safely — proving it's dead before it's gone.
When to Use This Skill
- A file or module feels heavier than what it does
- Before adding a feature to an already-cluttered area (clear the ground first)
- You see commented-out code,
// TODO (2023), orif (false)branches - An abstraction is used by exactly one caller
- A feature flag has been at one value for months
Don't use when: you can't yet prove the code is unused, or when "dead" code is actually a public API / plugin surface others depend on. When in doubt, prove first (step 2). For a small dead line you noticed while editing something else, don't open a deliberate sweep — that's boyscout territory (bounded, in-scope cleanup). This skill is the deliberate, repo-wide hunt.
Instructions
1. Inventory the candidates
Scan the target scope and list deletion candidates by category:
- Dead branches — conditions that can't be true (
if (false), flags pinned to one value) - Unused symbols — exports, functions, variables with no callers
- Commented-out code — version control already remembers it; the comment is noise
- Single-use abstractions — interfaces/factories/generics with exactly one implementation or caller
- Stale markers — TODOs/FIXMEs older than the problem they describe
- Orphaned config — flags, env vars, settings nothing reads
- Orphaned tests & deps — tests that only exercise code being deleted; package dependencies nothing imports once the sweep lands
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.
- 7d ago First seen · 91 lines · 102 tokens per session scan A 7839fcadb051
delete-this is a skill published in the GitHub repository mikestangdevs/craft-skills (4 stars, last pushed 2mo ago), licensed MIT. It adds 102 tokens to every session and 1,367 once invoked, about $0.0005 per session on Opus 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 2026-08-31.
Other skills, from other repositories
plumb-line-remediate
Use when applying findings from a plumb-line audit report — the builder has a report (or pasted findings) and wants the fixes made. Opt-in and separate from the audit, which is read-only and never fixes.
craft-fix
The Craftsman standard for driving fixes against an existing craft-audit workspace — "fix the findings", "fix SEC-003", "work through the audit", "start the climb". An ACTION skill, not a domain: it picks findings off the master tracker's climb sequence, re-verifies each is still real, gets the user's approval, and…
recipe-diagnose
Investigate problem, verify findings, and derive solutions.
audit
Project health audit and health check — architecture, performance, tests, dependencies, code quality. Use when assessing overall project health, before releases, or after refactors.
investigate
Investigate bugs and errors in Elixir/Phoenix — root-cause analysis for crashes, exceptions, stack traces, test failures. Use --parallel for deep 4-track investigation.
narrow-bare-rescue
Narrow bare rescue in Elixir so real errors like KeyError and typos propagate instead of being swallowed. Use to audit rescues and refactor error handling.