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 d-padmanabhan/agent-engineering-handbook --skill skills-continuous-improvementgit clone --depth 1 https://github.com/d-padmanabhan/agent-engineering-handbookWrote 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/d-padmanabhan/agent-engineering-handbook/skills-continuous-improvement)<a href="https://agentmods.dev/skills/d-padmanabhan/agent-engineering-handbook/skills-continuous-improvement"><img src="https://agentmods.dev/badge/skills/d-padmanabhan/agent-engineering-handbook/skills-continuous-improvement/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/d-padmanabhan/agent-engineering-handbook/skills-continuous-improvement"><img src="https://agentmods.dev/badge/skills/d-padmanabhan/agent-engineering-handbook/skills-continuous-improvement.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 9 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Rogue Agent · line 3 Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
- high Tool Misuse · line 85 Code deploys a privileged Kubernetes workload (privileged container, hostPath mount, or host namespaces). This grants root on the node and is a node/cluster takeover vector.Fix: Remove privileged, hostPath, and host-namespace settings from workloads. Use a least-privilege securityContext, drop capabilities, and avoid mounting the host filesystem.
- high Tool Misuse · line 85 Code deploys a privileged Kubernetes workload (privileged container, hostPath mount, or host namespaces). This grants root on the node and is a node/cluster takeover vector.Fix: Remove privileged, hostPath, and host-namespace settings from workloads. Use a least-privilege securityContext, drop capabilities, and avoid mounting the host filesystem.
- medium Agent Snooping · line 43 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 44 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 45 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 46 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 46 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 48 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00103 | $0.01856 |
| Opus 5 | $0.00051 | $0.00928 |
| Sonnet 5 | $0.00021 | $0.00371 |
| Haiku 4.5 | $0.00010 | $0.00186 |
Grade A, and why
skills-continuous-improvement 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 — 176 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skills Continuous Improvement
Use this skill for the recurring two-week quality pass over this repository's skills and the rules they pair with.
The goal is not churn. The goal is to keep the handbook current, safe, and useful for code generation.
Cadence
Run every two weeks, or sooner when:
- A rule changes and its companion skill may now be stale.
- A new skill is added.
- A skill with an eval suite changes its instructions, description, fixtures, or expected behavior.
- A user reports that agents still generate weak code despite existing guidance.
- A vendor/runtime changes defaults, versions, APIs, or best practices.
- Pre-commit, lint, or security checks reveal repeated issues.
Scope
Review both layers:
- Rules (
rules/*.mdc) - concise invariant gates and file-scoped policy. - Skills (
skills/*/SKILL.mdplus one-level references) - canonical workflows, explanations, and examples. - Skill evals (
skills/*/evals/evals.jsonand synthetic fixtures) - measurable behavior and regression coverage.
Ownership Contract
- A rule owns only requirements that must apply whenever its scope matches.
- A skill owns procedures, examples, command sequences, troubleshooting, and detailed references.
- A rule may summarize a gate and link to the skill, but must not copy the skill's tutorial content.
- A skill may link to a mandatory rule, but must not become a second policy source.
- Treat duplicated prose and bidirectional "canonical" claims as defects.
- Use supported Cursor activation metadata:
globsfor file-scoped rules and precisename/descriptionmetadata for skills. Do not invent unsupported skill frontmatter such aspaths. - Use absolute
${HANDBOOK_ROOT}/...links for cross-file handbook references so agents do not resolve them against another active repository.
Prioritize skills with paired rules first:
- Python rule (
${HANDBOOK_ROOT}/rules/200-python.mdc) ↔ Python skill (${HANDBOOK_ROOT}/skills/python-development/SKILL.md) - Go rule (
${HANDBOOK_ROOT}/rules/210-go.mdc) ↔ Go/Rust skill (${HANDBOOK_ROOT}/skills/go-rust-systems/SKILL.md) - JavaScript and TypeScript rule (
${HANDBOOK_ROOT}/rules/225-javascript-typescript.mdc) ↔ TypeScript/JavaScript skill (${HANDBOOK_ROOT}/skills/typescript-javascript/SKILL.md) - Bash rule (
${HANDBOOK_ROOT}/rules/140-bash.mdc) ↔ Bash skill (${HANDBOOK_ROOT}/skills/bash-shell-scripting/SKILL.md) and scripting automation skill (${HANDBOOK_ROOT}/skills/scripting-automation/SKILL.md) - Cloudflare rule (
${HANDBOOK_ROOT}/rules/400-cloudflare.mdc) / Cloudflare Workers rule (${HANDBOOK_ROOT}/rules/401-cloudflare-workers.mdc) / Cloudflare WAF rule (${HANDBOOK_ROOT}/rules/405-cloudflare-waf-rules.mdc) ↔ Cloudflare skills - Kubernetes rule (
${HANDBOOK_ROOT}/rules/450-kubernetes.mdc) / Helm rule (${HANDBOOK_ROOT}/rules/460-helm.mdc) ↔ Kubernetes containers skill (${HANDBOOK_ROOT}/skills/kubernetes-containers/SKILL.md) and Kubernetes operator development skill (${HANDBOOK_ROOT}/skills/kubernetes-operator-development/SKILL.md)
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 Changed 544b0f7bab8d
- 9d ago First seen · 176 lines · 103 tokens per session scan A fd98f7f2eae4
skills-continuous-improvement is a skill published in the GitHub repository d-padmanabhan/agent-engineering-handbook (17 stars, last pushed today), licensed MIT. It adds 103 tokens to every session and 1,856 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 2026-09-03.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…