autonomous-agent-patterns

Design patterns for building autonomous coding agents, inspired by [Cline](https://github.com/cline/cline) and [OpenAI Codex](https://github.com/openai/codex).

Quality

59%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills/skills/autonomous-agent-patterns/SKILL.md

The canonical home for this skill is autonomous-agent-patterns in sickn33/agentic-awesome-skills

Quality

Content

65%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is a well-organized, code-rich patterns catalog with strong actionability and efficient prose. Its main weaknesses are the absence of progressive disclosure (everything inlined into one large file with no reference files) and lack of explicit workflow checkpoints, though the latter is partly inherent to a reference-style skill.

Suggestions

Split large sections (e.g. Browser Automation, MCP Integration, Context Management) into separate reference files under references/ and link to them from SKILL.md to improve progressive disclosure.

Add a brief 'How to apply these patterns' sequenced workflow with validation checkpoints for actually assembling an agent from the catalog.

Define shared types (ToolResult) and include imports at the top so the code examples are fully copy-paste executable.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean executable code with minimal conceptual padding (no 'what is a PDF' style explanations), though at ~750 lines the sheer volume and some docstrings could be trimmed, fitting the score-4 'efficient, minor instances of over-explanation' anchor.	4 / 5
Actionability	Provides numerous concrete, largely copy-paste-ready Python class implementations (AgentLoop, EditFileTool, ApprovalManager, SandboxedExecution, BrowserTool), with only minor gaps such as undefined ToolResult/Any types and missing imports, matching the score-4 anchor.	4 / 5
Workflow Clarity	This is a patterns catalog, not a sequenced multi-step workflow; sections are logically numbered (1-6) with a best-practices checklist, but there are no explicit validation checkpoints or feedback loops, fitting the score-3 anchor.	3 / 5
Progressive Disclosure	No bundle files exist and the entire ~750-line catalog is inlined into SKILL.md; while section headers provide structure, content that arguably belongs in separate reference files is all inline, matching the score-3 anchor rather than the under-50-line exception.	3 / 5
	Total	14 / 20 Passed

Description

53%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description clearly states what the skill provides but omits any explicit 'when to use it' guidance, which caps completeness. Trigger terms are decent but lack common synonyms. Add a concrete 'Use when...' clause enumerating natural triggers to lift completeness and trigger quality.

Suggestions

Append an explicit trigger clause, e.g. 'Use when building autonomous AI/coding agents, designing tool-calling or function-calling APIs, or implementing permission/approval systems for agents.'

List concrete capabilities covered (agent loop, tool schemas, permission levels, sandboxing, browser automation, context/checkpoint management) so specificity reaches a 4-5 anchor.

Add common synonyms users actually say ('AI agents', 'agent loop', 'tool calling', 'function calling', 'human-in-the-loop') to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain ('building autonomous coding agents') and a concrete deliverable ('design patterns'), but offers no enumerated concrete actions, leaning toward the score-3 anchor's '1-2 concrete actions, not comprehensive'.	3 / 5
Completeness	Has a clear 'what' (design patterns for building autonomous coding agents) but no 'Use when...' trigger clause, so per the rubric completeness is capped at 3 when 'when' is missing.	3 / 5
Trigger Term Quality	Includes the natural phrase 'autonomous coding agents' plus product names 'Cline' and 'OpenAI Codex', but misses common synonyms users might say ('AI agents', 'agent loop', 'tool calling', 'function calling'), matching the score-3 anchor.	3 / 5
Distinctiveness Conflict Risk	The niche ('autonomous coding agents') plus explicit Cline/Codex references make it mostly distinct with only minor overlap risk against general agent-building skills, fitting the score-4 anchor.	4 / 5
	Total	13 / 20 Passed

Validation

87%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (765 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: plugins/AI-Agents-Safe-Coding-Skills/skills/autonomous-agent-patterns/SKILL.md
Commit: debb2ec

Reviewed: 1 day ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.