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 ckorhonen/claude-skills --skill agent-engineeringgit clone --depth 1 https://github.com/ckorhonen/claude-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/ckorhonen/claude-skills/agent-engineering)<a href="https://agentmods.dev/skills/ckorhonen/claude-skills/agent-engineering"><img src="https://agentmods.dev/badge/skills/ckorhonen/claude-skills/agent-engineering/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/ckorhonen/claude-skills/agent-engineering"><img src="https://agentmods.dev/badge/skills/ckorhonen/claude-skills/agent-engineering.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 | $0.00062 | $0.01919 |
| Opus 5 | $0.00031 | $0.00959 |
| Sonnet 5 | $0.00012 | $0.00384 |
| Haiku 4.5 | $0.00006 | $0.00192 |
Grade A, and why
agent-engineering 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 9d 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 — 223 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Engineering Principles
Battle-tested principles for AI coding agents that produce reliable, high-quality work.
When to Use This Skill
- Writing or reviewing an
AGENTS.md/CLAUDE.md/CURSOR.mdfile for a project - Configuring a new AI coding agent or subagent
- Diagnosing why an agent keeps making the same mistakes
- Reviewing agent output quality and identifying systemic issues
- Onboarding an agent to a complex codebase
1. Plan Mode Default
- Enter plan mode for ANY non-trivial task (3+ steps or architectural decisions)
- If something goes sideways, STOP and re-plan immediately — don't keep pushing
- Use plan mode for verification steps, not just building
- Write detailed specs upfront to reduce ambiguity
When to skip: Simple, single-file edits with obvious solutions.
Example plan format (tasks/todo.md):
## Task: Migrate auth to JWT
### Plan
- [ ] Audit current session-based auth flow
- [ ] Design JWT payload schema (user_id, roles, expiry)
- [ ] Implement token generation in auth service
- [ ] Update middleware to validate JWT
- [ ] Write tests for edge cases (expired, invalid, revoked)
- [ ] Update docs
### Done
- [x] Audit complete — 4 routes need updating
2. Subagent Strategy
- Use subagents liberally to keep main context window clean
- Offload research, exploration, and parallel analysis to subagents
- For complex problems, throw more compute at it via subagents
- One task per subagent for focused execution
Key insight: Context window pollution is the #1 cause of agent quality degradation. Subagents are cheap — use them.
When to spawn a subagent vs. do it inline:
| Use a subagent | Do inline |
|---|---|
| Research task (>10 files) | Simple 1-file edit |
| Independent parallel work | Quick config change |
| Long-running compilation or test run | Single command with clear output |
| Isolated experiment (risky change) | Trivial refactor |
3. Self-Improvement Loop
After ANY correction from the user:
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.
- 9d ago First seen · 223 lines · 62 tokens per session scan A 72a35b2d1369
agent-engineering is a skill published in the GitHub repository ckorhonen/claude-skills (14 stars, last pushed 2mo ago), licensed MIT. It adds 62 tokens to every session and 1,919 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
watch
File sentinel that monitors the working directory for changes and marker comments, then auto-triggers appropriate skills. Poll-based via git diff against the last scan commit. Writes intake items for batch processing and routes marker actions through /do. Use for automatic reactions to file changes; do NOT use for…
review
5-pass structured code review — correctness, security, performance, readability, consistency.
live-preview
Mid-build visual verification loop. Takes screenshots of components during construction, not just after. Catches visual regressions and invisible features before they compound. Requires Playwright or similar screenshot tool.
marshal
Meta-orchestrator that takes any direction — broad, specific, or vague — and autonomously chains skills and context into actionable work. Gathers context from codebase, docs, and memory. Only asks the user when it genuinely cannot proceed. Single-session orchestrator.
wiki
Markdown-first knowledge base where the LLM acts as librarian. Ingests raw sources, compiles and interlinks topic files, self-maintains an index. No vector DB or embeddings required -- uses LLM-native navigation over structured markdown up to 400K words.
huggingface-llm-trainer
Train or fine-tune language models with TRL or Unsloth on Hugging Face Jobs, including SFT, DPO, GRPO, reward models, and GGUF conversion. Use for cloud LLM training; use huggingface-vision-trainer for vision tasks.