Attempt Ledger
Productivityattempt-ledgerAttempt 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
QUICK START
How to use this skill
Bring this guide into your coding agent with a prompt tailored to the tool you use.
- Open your project in Codex.
- Copy and paste the prompt below.
- 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:
| Condition | Gating Action |
|---|---|
attempts >= max_attempts | Gate with max_attempts_exceeded |
| Same error repeated 2+ times | Gate with repeated_failure |
| Manual block by user | Gate 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:
- Git state: Current branch, last commit, uncommitted changes
- Epic context: Title, description, overall progress
- Task details: Files, acceptance criteria, dependencies
- Previous receipts: What was tried, what failed, why
This prevents context drift and ensures each attempt builds on prior learnings.
Commands
| Command | Purpose |
|---|---|
/relay:init | Create epic and ledger from blueprint |
/relay:status | Show progress and gated tasks |
/relay:work | Execute 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).