Index of every page on this site: llms.txt
All skills
affaan-m avatar

/continuous-agent-loop

@90606c8
by Affaan Mustafaaffaan-m/ecc287k stars
42,569
Run it yourself

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.

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

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

SKILL.md

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

Description uses 2.7% of example budget

Before choosing a Skill, your Agent reads its name and description. All available Skills share that space.

  • A shorter description leaves more room for other Skills. This entry exceeds our 1% size suggestion.

In our Claude Code example, all Skill names and descriptions share 8,000 characters. This Skill uses ≈215 characters, or 2.7%.

The 1% threshold is a size suggestion. Longer descriptions can still fit.

Your model, settings, and other Skills decide how much text your Agent can read.

Example settings and source

The example uses a 200k-token context and default Claude Code settings. The count includes the name, description, separators, and when_to_use when present. Codex also counts local file paths.

Skit's source and limits: Codex 0.160.1, Claude Code 2.1.292.

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

Skill behaviors

No rule matched.

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

Third-party checks

No alertstoday3 checks · Risk SAFE
  • Gen Agent Trust Hubtoday

    The skill is a documentation resource providing architectural patterns for continuous autonomous agent loops. It contains no executable code, network operations, or external dependencies, posing no security risk.

  • Sockettoday

    No alerts

  • Snyktoday

    Risk: LOW · No issues

Provenance

Signed by skilld at 90606c8. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 3 days 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/ecc/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.