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 kensaurus/cursor-kenji --skill plan-dead-codegit clone --depth 1 https://github.com/kensaurus/cursor-kenjiWrote 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/kensaurus/cursor-kenji/plan-dead-code)<a href="https://agentmods.dev/skills/kensaurus/cursor-kenji/plan-dead-code"><img src="https://agentmods.dev/badge/skills/kensaurus/cursor-kenji/plan-dead-code/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/kensaurus/cursor-kenji/plan-dead-code"><img src="https://agentmods.dev/badge/skills/kensaurus/cursor-kenji/plan-dead-code.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 | $0.00073 | $0.04675 |
| Opus 5 | $0.00036 | $0.02337 |
| Sonnet 5 | $0.00015 | $0.00935 |
| Haiku 4.5 | $0.00007 | $0.00468 |
Grade A, and why
plan-dead-code 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 today.
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 — 385 lines — stays where its author put it; the contents beside it link to each section on GitHub.
plan-dead-code — Prove it is dead before anyone deletes it
Degree of freedom: MIXED. Tool config authoring and the baseline
command set [LOW freedom — run exactly]; judging reachable vs
proven-dead, and what must keep working, [HIGH freedom].
Plan-only. This pass deletes nothing — not a file, not an export, not
a dependency, not a row. It produces plan-dead-code.md: a reviewed
keep/kill list plus a ratchet baseline.
The failure mode this skill exists to prevent: an agent runs knip on a
vibe-coded repo, gets 300 findings, and starts deleting. On a first run,
most findings are misconfiguration, not dead code. Knip's own docs are
explicit — running --fix "before your configuration is fully settled is
dangerous", and ignore patterns are "a last resort" because "hiding a
result is not the same as resolving it."
This skill vs neighbors
| Skill | Owns |
|---|---|
| plan-dead-code (this) | Nothing reaches this — unreachable files/exports/deps/assets/schema (plan only) |
housekeep-dead-code |
Execute this plan — delete by category, install the ratchet |
plan-stub-checker |
This reaches nothing — dead buttons, unwired handlers |
plan-antislop |
Looks machine-authored — a taste judgment, not reachability |
plan-dependency-provenance |
Package existence, integrity, licensing, slopsquatting |
audit-code-quality |
Repo-wide smells and consistency drift |
workflow-refactor |
Restructuring live code that stays |
enhance-arch-boundaries |
Circular deps and layer direction (dependency-cruiser) |
audit-db-schema |
Schema design, constraints, naming |
housekeep-backlog |
The TODO/skipped-test register |
workflow-housekeep |
README, build artifacts, dependency bumps |
Boundary with plan-dependency-provenance: it owns manifest facts (does
this package exist, is it licensed). This owns the graph fact (nothing
imports it). A package that is real, licensed, and unimported is this
skill's finding.
What ships with it
4 files 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.
- today First seen · 385 lines · 73 tokens per session scan A afd6828e4742
plan-dead-code is a skill published in the GitHub repository kensaurus/cursor-kenji (9 stars, last pushed yesterday), licensed MIT. It adds 73 tokens to every session and 4,675 once invoked, about $0.0004 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 2026-09-11.
Other skills, from other repositories
pre-mortem-facilitator
Facilitate a pre-mortem session using Shreyas Doshi's Tigers/Paper Tigers/Elephants framework. Use when the user is planning a launch, starting a critical project, preparing for a major initiative, or wants to proactively identify risks before something goes wrong.
systematic-debugging
Use when encountering bugs, test failures, unexpected behavior, or any technical issue before proposing fixes.
task
Use when creating, updating, or managing task files for projects and plans.
systemic-issue-triage
Trigger: new issue, bug report, triage, backlog, issue flood, community report, root cause, dead-end, blocked user. Attack issues by root class, never one-by-one; fixes must shrink the system, not grow it.
triage-bug-readiness
Use when assessing a Jira bug ticket for AI autofix readiness. Produces a structured JSON verdict (ready/needsinfo/notfixable) based on a three-gate rubric. Designed for CI pipeline use with the jira-triage orchestrator.
ai-bug-fix-triage
Triage JIRA bugs against repository code to classify AI fixability. Use when reviewing a backlog of bugs to determine which ones an AI agent can fix.