agent-rules-skill

A packaged “agent skill” that helps AI coding agents generate and maintain AGENTS.md files (and optional scoped subsystem variants) according to the agents.md specification. It includes scripts/templates for detecting project structure and stack signals and then producing/updating the agent context files idempotently with managed headers.

Evaluated Mar 30, 2026 (22d ago)
Repo ↗ DevTools agent-skills agents-md documentation templating idempotent developer-tools onboarding multi-language claude-code-skill
⚙ Agent Friendliness
43
/ 100
Can an agent use this?
🔒 Security
20
/ 100
Is it safe for agents?
⚡ Reliability
20
/ 100
Does it work consistently?

Score Breakdown

⚙ Agent Friendliness

MCP Quality
0
Documentation
70
Error Messages
0
Auth Simplicity
100
Rate Limits
0

🔒 Security

TLS Enforcement
20
Auth Strength
0
Scope Granularity
0
Dep. Hygiene
50
Secret Handling
40

No auth/network/API details are provided; primarily a local skill that generates documentation files. Security posture depends on the skill’s scripts/templates and how the agent runner executes them. Since documentation generation may read repo files (e.g., package.json/go.mod), ensure sensitive files aren’t unintentionally included in generated context. Dependency hygiene and secret handling are not verifiable from the provided content.

⚡ Reliability

Uptime/SLA
0
Version Stability
40
Breaking Changes
20
Error Recovery
20
AF Security Reliability

Best When

You want consistent, convention-based agent onboarding/context files across many repositories and languages, and you use agents that understand the agents.md / Agent Skills conventions (e.g., Claude Code/Cursor/Copilot skills or skill runners).

Avoid When

You need an authenticated remote service/API, strict security/compliance guarantees around telemetry/data retention (not specified here), or tight control over tool execution beyond the repository-local scripts/templates.

Use Cases

  • Generate an AGENTS.md for a repository to guide AI coding agents
  • Update/refresh AGENTS.md content while preserving existing structure
  • Create scoped AGENTS.md files per subsystem (e.g., backend/frontend/internal/cmd)
  • Validate AGENTS.md structure and conventions
  • Auto-extract relevant commands/version signals from common build/config files (e.g., Makefile/package.json/composer.json/go.mod)

Not For

  • Providing a general-purpose API for runtime app functionality
  • Handling real-time data fetching from external services
  • Replacing project README or documentation intended for humans as a primary source of truth

Interface

REST API
No
GraphQL
No
gRPC
No
MCP Server
No
SDK
No
Webhooks
No

Authentication

OAuth: No Scopes: No

No authentication mechanism described; usage appears to be installing a skill into an agent environment and running local/skill workflows.

Pricing

Free tier: No
Requires CC: No

Pricing not described; appears to be distributed via marketplace/package managers.

Agent Metadata

Pagination
none
Idempotent
True
Retry Guidance
Not documented

Known Gotchas

  • Skill keyword/trigger behavior is described at a high level; exact trigger phrases and how conflicts are resolved aren’t specified here.
  • Because it generates files, agents should ensure they don’t inadvertently commit undesired changes; the repo-local nature of updates may still cause diffs in agent-managed regions.
  • Idempotency quality depends on existing file structure matching expected conventions; unusual/manual AGENTS.md layouts may not preserve as intended.

Alternatives

Full Evaluation Report

Comprehensive deep-dive: security analysis, reliability audit, agent experience review, cost modeling, competitive positioning, and improvement roadmap for agent-rules-skill.

AI-powered analysis · PDF + markdown · Delivered within 30 minutes

$99

Package Brief

Quick verdict, integration guide, cost projections, gotchas with workarounds, and alternatives comparison.

Delivered within 10 minutes

$3

Score Monitoring

Get alerted when this package's AF, security, or reliability scores change significantly. Stay ahead of regressions.

Continuous monitoring

$3/mo

Scores are editorial opinions as of 2026-03-30.

8642
Packages Evaluated
17761
Need Evaluation
586
Need Re-evaluation
Community Powered