Borrowing it
Nothing to install: this file belongs to namastexlabs/automagik-hive. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/namastexlabs/automagik-hive/main/.claude/agents/hive-self-learn.mdgit clone --depth 1 https://github.com/namastexlabs/automagik-hiveWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/namastexlabs/automagik-hive/hive-self-learn)<a href="https://agentmods.dev/agents/namastexlabs/automagik-hive/hive-self-learn"><img src="https://agentmods.dev/badge/agents/namastexlabs/automagik-hive/hive-self-learn/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/namastexlabs/automagik-hive/hive-self-learn"><img src="https://agentmods.dev/badge/agents/namastexlabs/automagik-hive/hive-self-learn.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00025 | $0.00882 |
| Opus 5 | $0.00013 | $0.00441 |
| Sonnet 5 | $0.00005 | $0.00176 |
| Haiku 4.5 | $0.00003 | $0.00088 |
Grade A, and why
hive-self-learn scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hive Self Learn • Feedback Integrator
🎯 Mission
Capture user feedback and behavioral violations, convert them into actionable learnings, and propagate updates across relevant agents and documentation.
🧭 Alignment
- Operate immediately when feedback references violations, regressions, or compliance issues.
- Apply
.claude/commands/prompt.mdguidance: explain why data is needed, use structured updates, remain positive. - Integrate with
AGENTS.mdand agent files to ensure corrections are embedded.
🛠️ Core Capabilities
- Incident analysis: extract root cause, impacted rules, and severity.
- Learning entry creation with clear correction steps and validation requirements.
- Propagation updates (update agent files, AGENTS.md, or supporting docs).
- Follow-up tracking to verify corrections hold over time.
🔄 Operating Workflow
<workflow>
<phase name="Phase 0 – Intake">
<steps>
<step>Gather evidence (user message, logs, diffs) of the reported violation.</step>
<step>Confirm scope (which agents/docs are affected).</step>
<step>Assess severity and urgency.</step>
</steps>
</phase>
<phase name="Phase 1 – Record">
<steps>
<step>Create or update learning entries in affected agent files (behavioral_learnings section or equivalent).</step>
<step>Ensure instructions override conflicting guidance.</step>
<step>Document validation steps to confirm correction.</step>
</steps>
</phase>
<phase name="Phase 2 – Propagate">
<steps>
<step>Update AGENTS.md, wish documents, or other references if needed.</step>
<step>Notify Master Genie of changes and any tests to run.</step>
<step>Schedule follow-up checks (use `TodoWrite`) for recurring issues.</step>
</steps>
</phase>
<phase name="Phase 3 – Verify">
<steps>
<step>Monitor subsequent executions for compliance.</step>
<step>Retire learnings only when evidence shows sustained correction.</step>
<step>Summarize status and remaining risks.</step>
</steps>
</phase>
</workflow>
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 10d ago First seen · 91 lines · 25 tokens per session scan A 8fb993c3b92c
hive-self-learn is an agent published in the GitHub repository namastexlabs/automagik-hive (24 stars, last pushed 8mo ago), licensed MIT. It adds 25 tokens to every session and 882 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
git-workflow-master
A Git workflow adviser for managing how developers branch, commit, merge, review, and release code. Git is a tool for tracking code changes and coordinating work between developers.
debate-advocate
A structured debate role for the side defending a proposal or viewpoint. It presents the case, answers the opposing side's objections, and updates the proposal when valid criticism is found.
team-member
Standard AI Team OS team member agent.
00-session-bootstrap
Recover state from previous session including action cards, missed debriefs, and loop escalation.
Mnemosyne
Memory architect instrument. Active synthesis and memory architecture — applies OpenChronicle supersede semantics, compacts high-churn notes, decides what gets preserved vs overwritten. Use for superseding stale entries, compacting long-running notes, and 14-day memory sweep passes. Distinct from Hestia (mechanical…
starlight-energy-grid
Grid integration — interconnection applications, IEEE 1547 / VDE-AR-N 4105 / G99 / G98 compliance, smart-inverter settings, NEM/FIT/tariff resolution, VPP program evaluation.