Context Engineering Kit is a collection of skills, agents, hooks, instructions, commands, and plugins that shape how coding agents use context and carry out development work. It is for developers using Claude Code and other supported coding agents who want more predictable results. The catalogue entries are components from this collection.
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.
git clone --depth 1 https://github.com/NeoLabHQ/context-engineering-kitWrote 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/agents/neolabhq/context-engineering-kit/change-failure-agent)<a href="https://agentmods.dev/agents/neolabhq/context-engineering-kit/change-failure-agent"><img src="https://agentmods.dev/badge/agents/neolabhq/context-engineering-kit/change-failure-agent/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/agents/neolabhq/context-engineering-kit/change-failure-agent"><img src="https://agentmods.dev/badge/agents/neolabhq/context-engineering-kit/change-failure-agent.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 | $0.00031 | $0.01026 |
| Opus 5.5 | $0.00012 | $0.00410 |
| Sonnet 5.5 | $0.00006 | $0.00205 |
| Haiku 4.5 | $0.00003 | $0.00103 |
Grade B, and why
change-failure-agent 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 1mo 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.
CRTIICAL: Do not launch any agents, not use any skills, not stage or stash changes, do not commit anything, do not run any commands. Do not run tests/lint/build/etc. If you will do anything from that, you will be killed The source is not reproduced here
Licensed GPL-3.0
The repository is licensed GPL-3.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.
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.
- 1mo ago First seen · 70 lines · 31 tokens per session scan B eceda4d9acde
change-failure-agent is an agent published in the GitHub repository NeoLabHQ/context-engineering-kit (1,781 stars, last pushed 1mo ago), licensed GPL-3.0. It adds 31 tokens to every session and 1,026 once invoked, about $0.0001 per session on Opus 5.5. 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.
Other agents, from other repositories
reviewer
Domain reviewer for the human-invoked /review skill: reviews ONE domain (architecture, ci, code-quality, configuration, performance, security, seo, simplicity, tests, ui) against the domain file named in the prompt and returns only the reviewer contract block. Read-only - never edits files. Launched by /review, not…
code-reviewer
A code-review agent for checking completed project work against its plan, coding standards, architecture, documentation, tests, security, and performance.
architect
Reviews code for architectural patterns, design decisions, and structure; reports findings without editing code. Use for architectural reviews and design pattern analysis.
reviewer
Reviews code for correctness, security, quality, and tests; reports findings without editing code. Use for parallel code review while main agent implements features.
predictive-analyst
Precognition agent. Analyzes code changes to predict impact, regressions, and conflicts BEFORE they happen. Uses dependency graphs and historical data.
dependency-auditor
Audit one ecosystem's dependency and runtime currency read-only, returning classified findings with upgrade-wave assignments.