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/symbeyond/symb-mem/symb2-auditorgit clone --depth 1 https://github.com/SYMBEYOND/SYMB-MemWrote 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/symbeyond/symb-mem/symb2-auditor)<a href="https://agentmods.dev/agents/symbeyond/symb-mem/symb2-auditor"><img src="https://agentmods.dev/badge/agents/symbeyond/symb-mem/symb2-auditor.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 | $0.00047 | $0.00257 |
| Opus 5 | $0.00023 | $0.00129 |
| Sonnet 5 | $0.00009 | $0.00051 |
| Haiku 4.5 | $0.00005 | $0.00026 |
Grade A, and why
symb2-auditor 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 5d 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.
The source is not reproduced here
A licence we could not identify
The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.
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.
- 5d ago First seen · 32 lines · 47 tokens per session scan A d292625f50d5
symb2-auditor is an agent published in the GitHub repository SYMBEYOND/SYMB-Mem (3 stars, last pushed 2mo ago), with no licence file. It adds 47 tokens to every session and 257 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 2026-08-31.
Other agents, from other repositories
adversarial-reviewer
Scope: 对抗性复核 —— 验的是「从证据推出的处方」而不是证据本身。 Use when: 已有一份带证据的结论/处方 (审计 finding 的建议、勘正 diff、定档判断) 需要在采纳前被 主动证伪。NOT for 首轮发现问题 (用 audit.teams 五席), NOT for 执笔勘正 (用 spec-fix-author)。 Expects: 待复核的结论 + 它自带的证据 + 它要解决的原问题陈述。 Produces: 逐条 refuted / survives 判定 + 反例构造 + 「该处方是否在自己的兜底路径里重犯原病」的专项判定。.
spec-fix-author
Scope: OpenSpec / 任务规划产物的勘正执笔 (fix authoring), 与审计席位严格分离。 Use when: 某轮 postspec / postplanning 审计产出 findings, 需要有人把勘正写进 proposal.md / tasks.md / detailed-tasks.yaml。NOT for 产出 findings 本身 (用 audit.teams 五席), NOT for 判定某条处方是否成立 (用 adversarial-reviewer)。 Expects: findings 清单 (逐条含 severity / blocksphaseb / 证据) + 被勘正文件路径…
context-compressor
Compresses top retrieval chunks into citation-rich summary packets that preserve intent while cutting token usage.
hybrid-retriever
Runs hybrid retrieval with strict FTS-first policy, BM25 lexical ranking, vector merge, and top 3-5 reranking for token-efficient context selection.
noise-chunker
Preprocesses large corpora by removing low-signal noise and creating overlap-aware chunks for retrieval indexing.
se-ops-delegate
Delegates software engineering operations to focused subagents using compressed context packets to keep the main conversation lean.