Individual skill
agents-best-practices
Use when designing, auditing, refactoring, or explaining an agentic harness for any domain, especially when work must continue from a measured gap to verified completion. Covers provider-neutral loops, tools, permissions, environment adaptation, planning, durable workflow state, context, skills, observability, evals, and safety for OpenAI, Anthropic, and compatible APIs. Not for implementing an ordinary app feature or reviewing one concrete diff.
skills/agents-best-practices/SKILL.md
Source commit 849719987d9c0d6ed973bdbce8ed37b266d3b1f3
What was checked
- Matches the observed repository HEAD
- Yes
- Scanner rules are current
- No
- Repository scan complete
- No
- Skill scan complete
- No
- Observed behavior
- Not checked yet
- Last checked
- Nov 7, 2026
These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.
Install this skill
Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.
An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.
Repository context
- Repository stars (not skill ratings)
- 214
- Repository last updated
- Nov 7, 2026
- License
- MIT
Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.
- ai-agents Repository topic
- claude Repository topic
- claude-code Repository topic
- llm Repository topic
- machine-learning Repository topic
- prompt-engineering Repository topic
- skills Repository topic
- mcp Repository topic
- agent-harness Repository topic
- harness Repository topic
- operations Derived category
Files and excerpt
File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.
Browse files
ATTRIBUTION.mddoc · 844 bytesLICENSE-upstreamasset · 1,071 bytesSKILL.mdcore · 21,723 bytesreferences/agent-legibility-feedback-loops.mddoc · 7,773 bytesreferences/agentic-loop.mddoc · 6,875 bytesreferences/architecture.mddoc · 9,272 bytesreferences/checklists.mddoc · 15,819 bytesreferences/coding-agents.mddoc · 17,505 bytesreferences/completion-reconciliation.mddoc · 7,004 bytesreferences/context-memory-compaction.mddoc · 8,027 bytesreferences/coverage-audit.mddoc · 8,367 bytesreferences/environment-adaptive-tools.mddoc · 22,372 bytesreferences/evals.mddoc · 14,161 bytesreferences/mvp-agent-blueprint.mddoc · 16,502 bytesreferences/planning-and-goals.mddoc · 7,362 bytesreferences/prompt-caching-and-cost.mddoc · 7,586 bytesreferences/provider-api-patterns.mddoc · 7,435 bytesreferences/security-observability.mddoc · 6,706 bytesreferences/self-refining-recursive-harnesses.mddoc · 26,134 bytesreferences/skills-and-connectors.mddoc · 8,849 bytesreferences/source-links.mddoc · 7,681 bytesreferences/speculative-tool-execution.mddoc · 18,409 bytesreferences/system-prompts-instructions.mddoc · 4,430 bytesreferences/tools-and-permissions.mddoc · 8,360 bytesreferences/workflow-orchestration.mddoc · 13,486 bytes
Read excerpt
# Agents Best Practices
Use this skill when the user asks how to build, improve, debug, or evaluate an agentic harness. This is a general-purpose agent architecture skill. Coding agents are one subdomain only; apply the same principles to research, finance, legal, support, operations, sales, healthcare, education, data analysis, procurement, and workflow automation agents.
## Core stance
An agent harness is the control plane around a model. The model proposes actions; the harness validates, authorizes, executes, records, summarizes, and returns observations. Keep the loop simple and make the runtime rigorous.
Default architecture:
```text
user/task
-> instruction and context builder
-> model call