mcpbeat

Hive Error Recovery

aden-hive/hive.error-recovery

Follow a structured recovery decision tree when tool calls fail instead of blindly retrying or giving up.

346 tokens
context cost
the whole folder, loaded on every use
1
files
instructions only
0
copies elsewhere
how many repositories repackaged it
10839
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository 
npx skills add https://github.com/aden-hive/hive --skill hive.error-recovery

The instruction itself

1 sections, as written by the author

Operational Protocol: Error Recovery

When a tool call fails:

  • Diagnose — classify the failure as *transient* (network blip, rate limit, timeout) or *structural* (wrong selector, missing auth, invalid schema, permission denied).
  • Decide:
  • Transient → retry once.
  • Structural + fixable → fix the input and retry.
  • Structural + unfixable → record the failure and move to the next item.
  • Blocking all progress → escalate.
  • Adapt — if the same tool has failed {{max_retries_per_tool}}+ times in a row, stop using it and find an alternative approach.

Never silently drop a failed item. If the item is a task in the colony queue, write the failure to the DB instead of an in-memory buffer:

sqlite3 "$DB_PATH" "UPDATE tasks SET status='failed', last_error='<one-sentence reason>', completed_at=datetime('now'), updated_at=datetime('now') WHERE id='<task-id>' AND worker_id='<your-worker-id>';"

The tasks.retry_count column and the stale-claim reclaimer handle auto-retry for crashes; your job is the within-run decision tree above. See hive.colony-progress-tracker for the full queue protocol.

How to use it

Copy the folder

Take aden-hive/hive.error-recovery from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.