dead-ends

dead-ends is a skill for Claude Code, Codex from karanb192/claude-code-hooks. It costs 22 tokens per session (215 once invoked), scanned B, original, MIT.

A repository record of approaches that were tried and abandoned, including why they failed and what they cost.

In plain words
What is it for?
Use it to list the most relevant abandoned approaches and flag earlier attempts that relate to the current work.
Why use it?
It prevents the team from unknowingly repeating previous dead ends.

Skill for Claude CodeCodex

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the dead-end-registry plugin — 1 skill shipped together

Install

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.

agentmods
npx agentmods add skills/karanb192/claude-code-hooks/dead-ends
Any agent
npx skills add karanb192/claude-code-hooks --skill dead-ends
Clone the repo
git clone --depth 1 https://github.com/karanb192/claude-code-hooks

Made for: Claude Code, Codex.

Or install dead-end-registry, the plugin that ships this one along with the rest of its 1 skill.

Wrote 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.

agentmods badge for dead-ends

README.md
[![agentmods](https://agentmods.dev/badge/skills/karanb192/claude-code-hooks/dead-ends.svg)](https://agentmods.dev/skills/karanb192/claude-code-hooks/dead-ends)
Your own site
<a href="https://agentmods.dev/skills/karanb192/claude-code-hooks/dead-ends"><img src="https://agentmods.dev/badge/skills/karanb192/claude-code-hooks/dead-ends.svg" alt="Measured on agentmods" height="20"></a>
Per session 22 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 215 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00022 $0.00215
Opus 5 $0.00011 $0.00108
Sonnet 5 $0.00004 $0.00043
Haiku 4.5 $0.00002 $0.00021

Measured 4d ago against content hash 0234782ddfb7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

dead-ends scanned grade B with 1 finding 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 4d 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.

Unrestricted tool accessmediumExcessive agency

A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.

empty, just say so. Keep it short; do not re-run any commands.
plugins/dead-end-registry/skills/dead-ends/SKILL.md · 19 lines

What it actually says

Dead ends

!node "${CLAUDE_SKILL_DIR}/../../dead-end-registry.js" --render 2>/dev/null || node "${CLAUDE_PLUGIN_ROOT}/dead-end-registry.js" --render

The list above is this repository's recorded dead ends: approaches that were tried and then reverted or ruled out, newest first, each with the date it was tried, why it was walked back, and the estimated token cost of the detour. It is produced by the dead-end-registry hook, which mines your transcripts as you work.

Briefly summarize the 1-3 most relevant entries and, if any bear on what the user is currently doing, gently flag that they have been down this road before. If the list is empty, just say so. Keep it short; do not re-run any commands.

Changes

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.

  1. 4d ago First seen · 19 lines · 0 tokens per session scan B 0234782ddfb7

Subscribe to this mod's changes

dead-ends is a skill published in the GitHub repository karanb192/claude-code-hooks (494 stars, last pushed 11d ago), licensed MIT. It adds 22 tokens to every session and 215 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

system-audit

Periodic evidence-based self-audit of the whole agent system — the orchestrator, its docs/SSOTs, rules, memory, subagents, tools, infra and the work it claims to have delivered — followed by immediate cheap-safe fixes and a ranked backlog. Use when the user says 'аудит системы', 'проверь себя', 'самопроверка', 'system…

awrshift/claude-memory-kit · 225 tokens

session-review

End-of-session adversarial review loop. Assemble the session's work into a role-assigned, self-contained brief, then run independent reviewers in parallel — an isolated code-reader (the idea-validator agent) that reads the ACTUAL files and web-checks technology currency, plus an external-family model if you have one …

awrshift/claude-memory-kit · 149 tokens

close-session

End-of-session ritual — audit today's patterns against accumulated memory, propose promotions, refresh MEMORY.md, and write the session handoff. Use when the user says "/memory-kit:close-session", "закрой сессию", "закрываем", "we're done for today", "wrap up".

awrshift/claude-memory-kit · 64 tokens

memory-audit

Audit MEMORY.md against the memory discipline — oversized sections, settled multi-session patterns that belong in knowledge/concepts/, stacked chronicle blocks, stale entries. Produces a move plan as a table for approval, then executes the approved moves atomically. Use when the SessionStart hook reports a tripped…

awrshift/claude-memory-kit · 119 tokens

second-opinion

Cross-check the agent's own answer with independent reviewers before bringing it to the user. Use when the user says 'second opinion', 'sanity check', 'cross-check', 'am I missing something', 'stress-test', 'devil's advocate', 'run a full review', 'this is important', 'high-stakes', 'help me choose between', 'critique…

awrshift/claude-memory-kit · 130 tokens

qa-sweep

Run a multi-lens agent QA sweep of the RUNNING product: spawn qa agents (one per lens — user-flow · edge-state · honesty · contract · ux-critique), collect their structured findings, integrator-verify the load-bearing ones, and land verified findings as backlog tickets + a run record in the project's qa/ folder. Use…

awrshift/claude-memory-kit · 199 tokens