keephive-helper
Skill1 starsChanged 9 months agoMITView on GitHub
Keep Claude Code sessions synced with the keephive knowledge loop.
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 0 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 25
Call hive status at session start for streaks, TODOs, and backend health.
- Very specific: line 26
When code changes slow down, run hive reflect for pattern spotting.
- Very specific: line 44
No LLM backend available ⇒ keephive queues the work.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Keephive Helper – Claude Code
What this skill does
- Keeps your agent synced with the keephive knowledge loop: memory (
hive remember), recall (hive recall), verification (hive verify), reflection (hive reflect), audit (hive audit). - Uses keephive MCP tools over stdio so every agent instance—local or remote—can query the same data store (
keephive mcp-serve). - Surfaces TODOs, rules, and daily logs so follow-ups never get lost between prompts.
Quick reactions
| Situation | Say this | What happens |
| Capture a fact | fact: <detail> | Invokes hive remember with FACT: prefix |
| Log a decision | decision: <rationale> | Writes decision entry, suggests follow-up verify |
| Need prior context | search logs for <topic> | Calls hive recall and shares top matches |
| Task drifting | todo: <task> | Adds TODO, mirrors in dashboard + session reminders |
| Unsure about freshness | verify <topic> | Runs hive verify, reports results or queues follow-up |
Session hygiene
- Call
hive statusat session start for streaks, TODOs, and backend health. - When code changes slow down, run
hive reflectfor pattern spotting. - Finish long sessions with
hive auditto capture action items.
MCP endpoints your agent can call
hive_recall– semantic + keyword search over memory/logs/TODOs.hive_status– structured session summary (facts/TODOs/streaks/backend state).hive_remember– store new facts/decisions/insights (automatically prefixes).hive_todo– CRUD for TODO list items.hive_verify– queue structured verification tasks when your LLM backend supports tools.hive_guides– fetch bundled guides and skill prompts.
Claude Code specifics
- Hooks: SessionStart, PreCompact, PostToolUse, UserPromptSubmit, Stop, SessionEnd, TaskCompleted all call keephive helpers. Keep them enabled for full telemetry.
- Binary path:
claude -pstays available, but keephive falls back to API/Gemini/OpenAI when needed. - Skill location:
~/.claude/skills/keephive-helper/SKILL.md(auto-updated byhive setup). - Telemetry: rich session metrics pulled from
~/.claude/usage-data/; dashboards merge them with keephive telemetry.
Need to recover?
- No LLM backend available ⇒ keephive queues the work; rerun when API keys/CLI return.
- Reset hooks ⇒
hive setup --platform claude --yesre-syncs skill + scripts. - Manual removal ⇒ delete the
keephive-helperskill file and rerunhive setup.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

