OpenParable
Skip to content
← Back to skills

Attempt Ledger

Productivity
attempt-ledger

Attempt Ledger is an Agent Skill for productivity published in the majiayu000/claude-skill-registry repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.

Knowledge about attempt tracking and gating patterns for task execution

View on GitHub ↗
QUICK START

How to use this skill

Bring this guide into your coding agent with a prompt tailored to the tool you use.

  1. Open your project in Codex.
  2. Copy and paste the prompt below.
  3. Review files and risks before approving any action.
Prompt to paste
Inspect the Agent Skill at https://github.com/majiayu000/claude-skill-registry/blob/HEAD/skills/workflow/attempt-ledger-majesticlabs-dev-majestic-marketplace/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/attempt-ledger, but wait for my approval before writing files or running scripts.

Copying this prompt does not install or run the skill. Review third-party files before use.

Attempt Ledger Pattern

Purpose

The attempt ledger tracks execution attempts for tasks, enabling:

  • Retry with context: Each attempt includes previous failure information
  • Gating: Prevents infinite retry loops when tasks consistently fail
  • Progress persistence: Resume execution after interruption
  • Receipt tracking: Structured summaries instead of full transcripts

Schema

# .majestic/attempt-ledger.yml
version: 1
epic_id: "20260111-feature-name"
started_at: "2026-01-11T17:30:00Z"

settings:
  max_attempts_per_task: 3
  timeout_minutes: 15
  review:
    enabled: true
    provider: repoprompt  # repoprompt | gemini | none

task_status:
  T1: completed
  T2: in_progress
  T3: pending
  T4: blocked

attempts:
  T1:
    - id: 1
      started_at: "..."
      ended_at: "..."
      result: success
      receipt:
        summary: "Created migration and model"
        files_changed: [file1.rb, file2.rb]

  T2:
    - id: 1
      result: failure
      receipt:
        error_category: missing_dependency
        error_summary: "Database not migrated"
        suggestion: "Run db:migrate first"

gated_tasks:
  T5:
    reason: "max_attempts_exceeded"
    gated_at: "..."

Gating Rules

Tasks are gated (blocked from retry) when:

ConditionGating Action
attempts >= max_attemptsGate with max_attempts_exceeded
Same error repeated 2+ timesGate with repeated_failure
Manual block by userGate with user_blocked

Receipt Structure

Success Receipt

receipt:
  summary: "Brief description of what was done"
  files_changed: [list, of, files]
  tests_passed: true

Failure Receipt

receipt:
  error_category: missing_dependency | code_error | test_failure | timeout
  error_summary: "What went wrong"
  approach_taken: "What was attempted"
  suggestion: "What to try differently"

Task Status Flow

pending → in_progress → completed
                ↓
            failure → pending (retry)
                ↓
            max_attempts → gated

Integration with Re-anchoring

Each fresh Claude instance receives:

  1. Git state: Current branch, last commit, uncommitted changes
  2. Epic context: Title, description, overall progress
  3. Task details: Files, acceptance criteria, dependencies
  4. Previous receipts: What was tried, what failed, why

This prevents context drift and ensures each attempt builds on prior learnings.

Commands

CommandPurpose
/relay:initCreate epic and ledger from blueprint
/relay:statusShow progress and gated tasks
/relay:workExecute tasks with attempt tracking

Configuration

In .agents.yml:

relay:
  max_attempts_per_task: 3
  timeout_minutes: 15
  review:
    enabled: true
    provider: none  # repoprompt | gemini | none

Override locally in .agents.local.yml (gitignored).