skilld
All skills
affaan-m avatar

/continuous-agent-loop

@d29cf65
by Affaan Mustafaaffaan-m/everything-claude-code270k stars
40,422

Patterns for continuous autonomous agent loops with quality gates, evals, and recovery controls. Use when running an agent loop that must self-check, gate on evals, and recover from failures.

Ask your Agent

Use this Skill: https://skilld.dev/gh/affaan-m/everything-claude-code/continuous-agent-loop

This session only. Nothing lands on disk.

SKILL.md

≈54 tokens always: the name and description. ≈231 when used: this file.

Continuous Agent Loop

This is the v1.8+ canonical loop skill name. It supersedes autonomous-loops while keeping compatibility for one release.

Loop Selection Flow

Start
  |
  +-- Need strict CI/PR control? -- yes --> continuous-pr
  |
  +-- Need RFC decomposition? -- yes --> rfc-dag
  |
  +-- Need exploratory parallel generation? -- yes --> infinite
  |
  +-- default --> sequential

Combined Pattern

Recommended production stack:

  1. RFC decomposition (ralphinho-rfc-pipeline)
  2. quality gates (plankton-code-quality + /quality-gate)
  3. eval loop (eval-harness)
  4. session persistence (nanoclaw-repl)

Failure Modes

  • loop churn without measurable progress
  • repeated retries with same root cause
  • merge queue stalls
  • cost drift from unbounded escalation

Recovery

  • freeze loop
  • run /harness-audit
  • reduce scope to failing unit
  • replay with explicit acceptance criteria

Source: SKILL.md on GitHub

Third-party checks

No alerts17d5 checks · Risk SAFE
  • Gen Agent Trust Hub17d

    This skill serves as a documentation-only resource, providing architectural patterns for autonomous agent loops. It contains no executable code, scripts, network operations, or sensitive commands, and presents no security risk.

  • Socket17d

    No alerts

  • Snyk17d

    Risk: LOW · No issues

  • Runlayer7mo

    1/1 file flagged

  • ZeroLeaks5mo

    Score: 93/100 · 2 sections analyzed

Provenance

Signed by skilld at d29cf65. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 14 hours ago.

Activeupdated 2 months ago

Capability

metadata
{
  "origin": "ECC"
}

Topics

  • continuous-integration
  • autonomous-agents
  • quality-gates
  • evaluation
  • loop-patterns
  • agent-control
  • pr-workflow
  • failure-recovery

README badge

README badge for affaan-m/everything-claude-code/continuous-agent-loop

What it does

Provides decision trees and patterns for structuring autonomous agent loops with quality gates, evaluations, and recovery controls. Covers sequential, RFC-decomposed, parallel, and CI/PR-integrated loop modes, with failure detection and cost-control strategies.

Generated from the current SKILL.md.

Frequently asked

Which loop pattern should I use for CI/PR workflows?
Use continuous-pr if you need strict CI/PR control. The skill provides a decision tree: choose rfc-dag for RFC decomposition, infinite for exploratory parallel generation, or sequential as the default.
What quality gates does this skill support?
The skill recommends combining plankton-code-quality with /quality-gate. It also integrates eval-harness for evaluation loops as part of the production stack.
How do I prevent loop churn and unbounded cost escalation?
The skill identifies loop churn, repeated retries, and cost drift as failure modes. Recovery involves freezing the loop, running /harness-audit, reducing scope to the failing unit, and replaying with explicit acceptance criteria.
What persistence mechanism does this skill use?
The recommended production stack includes nanoclaw-repl for session persistence, allowing the agent loop to maintain state across iterations.

Generated from the current SKILL.md. These answers refresh after source changes.