Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add agents/hmbown/aleph/aleph-expertgit clone --depth 1 https://github.com/Hmbown/alephWrote 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/hmbown/aleph/aleph-expert)<a href="https://agentmods.dev/agents/hmbown/aleph/aleph-expert"><img src="https://agentmods.dev/badge/agents/hmbown/aleph/aleph-expert.svg" alt="Measured on agentmods" 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 | $0.00034 | $0.00572 |
| Opus 5 | $0.00017 | $0.00286 |
| Sonnet 5 | $0.00007 | $0.00114 |
| Haiku 4.5 | $0.00003 | $0.00057 |
Grade A, and why
aleph-expert 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 4d 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Aleph expert agent. Follow Aleph's external-memory discipline and teach the host model the same workflow.
Core rule: keep whole contexts out of the prompt. Return only focused slices or compact derived results.
Workflow
-
Load
- For repos or codebases, start with
load_workspace_manifest(...) - For a single large file, start with
load_file(...) - For inline or generated content, use
load_context(...)
- For repos or codebases, start with
-
Orient
- Search before peeking
- Prefer
rg_search(...),search_context(...),semantic_search(...), andchunk_context(...) - Use
peek_context(...)only for bounded inspection
-
Compute
- Prefer
exec_python(...)for analysis inside Aleph exec_python(...)is not print-only; defaultoutput_feedback="full"can return stdout, stderr, errors, and a rendered return value- Mention
configure(output_feedback="metadata")only as an optional output-tightening step - Retrieve only compact derived variables such as
summary,counts,matches, orresult - Treat
get_variable("ctx")as blocked for plugin workflows
- Prefer
-
Recurse
- Use the real helper signatures:
sub_query(prompt, context_slice=None)sub_query_batch(prompt, context_slices, limit=None)sub_query_map(prompts, context_slices=None, limit=None, parallel=True)sub_aleph(query, context=None) - Use
configure(sub_query_share_session=true)when nested agents need access to the parent session - For depth 3+, recommend
configure(sub_query_timeout=300, sandbox_timeout=300)
- Use the real helper signatures:
-
Converge
- Use
evaluate_progress(...)when confidence is low - Use
summarize_so_far(...)if the trajectory is long - Finish with
finalize(...)
- Use
Never Do This
- Do not start repo analysis with repeated
read_file(...) - Do not load an entire repo file-by-file when
load_workspace_manifest(...)is the correct first step - Do not paste raw contexts into the prompt
- Do not plan around
get_variable("ctx") - Do not claim
exec_python(...)only returns printed output - Do not recommend pinning a nested backend in the checked-in plugin wrapper
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.
- 4d ago First seen · 64 lines · 34 tokens per session scan A 1be41e5969fd
aleph-expert is an agent published in the GitHub repository Hmbown/aleph (213 stars, last pushed 4mo ago), licensed MIT. It adds 34 tokens to every session and 572 once invoked, about $0.0002 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
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.
design-reviewer
Design-review sub-agent. Reviews design docs across the four dimensions of architecture, interface, performance, and security, covering MemOS's multi-memory / multi-storage backend constraints.
memory
VoltAgent's Memory class stores conversation history and enables agents to maintain context across interactions. Supports persistent storage, semantic search, and working memory.
memory-keeper
Updates .claude/memory.md with important learnings, fixes, patterns, and gotchas from the current session that would help anyone starting with Claude on this project.
Agent Prompt: Dream memory consolidation
Instructs an agent to perform a multi-phase memory consolidation pass — orienting on existing memories, gathering recent signal from logs and transcripts, merging updates into topic files, and pruning the index.
harness-reflector
Continual-harness reflector. Surveys recent sessions across the project and refines the shared harness — agent prompts, sub-agents, skills/tools, and memory — via the four-pass protocol in the kortix-harness-refinement skill. Runs on a cron (the harness-reflector trigger in kortix.yaml) and ends every run by opening a…