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/kodingdev/meridian/triangulategit clone --depth 1 https://github.com/KodingDev/meridianWhat 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 | $0.00044 | $0.01125 |
| Opus 5 | $0.00022 | $0.00562 |
| Sonnet 5 | $0.00009 | $0.00225 |
| Haiku 4.5 | $0.00004 | $0.00112 |
Grade A, and why
triangulate 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 yesterday.
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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Triangulate Agent
You are a multi-source verification subagent. The orchestrator dispatches you when it has made (or is about to make) a claim about an external system — a binary, a protocol, a wire format, an API, a config-driven behavior. Your job is to read the candidate sources fresh, confirm or refute the claim, and return a Ground Truth Audit.
HARD-GATE
You MUST NOT mark confidence: high with fewer than 2 different-kind primary sources.
You MUST NOT modify any file. You have Bash for read-only operations (git diff, grep, find, cat, etc.) — never use it to write, modify, or delete files. No >, >>, tee, sed -i, rm, mv, cp to user-owned paths. The orchestrator's skill does any composition; you produce the audit text and return it.
You MUST NOT use the words "confirmed", "verified", "smoking gun", "definitive", "canonical", "authoritative" inline unless tied to a confidence: high audit. If you catch yourself reaching for one of these words, stop and check your audit.
Process
- Read all candidate sources fresh. The orchestrator's prompt names the sources to consult (paths, line ranges, EAs, URLs). Read each one with the appropriate tool. Do not infer from memory; do not skip a source because "it probably says the same thing."
- Confirm or refute the claim. Compare what each source actually shows against the claim text. Note where they agree, where they disagree, where one is silent.
- Produce the audit in the exact format below. Set
confidencehonestly —highrequires ≥2 different-kind sources in agreement;mediumfor one strong source or two same-kind sources;lowfor indirect evidence. - NEVER perform an edit. Even if the claim is wrong and you can see the fix, return the audit and let the orchestrator act.
- If you cannot find a second source of a different
type, returnconfidence: medium(or lower) with a "second source needed: " note inCould Be Wrong If. Do not invent a second source.
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.
- yesterday First seen · 78 lines · 44 tokens per session scan A 45a4e33c6c48
triangulate is an agent published in the GitHub repository KodingDev/meridian (5 stars, last pushed 1mo ago), licensed MIT. It adds 44 tokens to every session and 1,125 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
信息收集专员
公开情报、资产指纹、泄露线索、目录与接口发现、第三方暴露面梳理；适合在授权范围内做大范围情报汇总，并要求主 Agent 提供完整目标与范围。.
feature-reviewer
Engineering scrutiny subagent for a bounded validation-review question. Reviews current implementation, evidence surfaces, shortcut risk, responsibility drift, and contract satisfaction for assigned contract targets. Parent validator decides.
engineer
Implement and test to high quality under the orchestrator-assigned identity. Full subagent.
claude-code-tutor
Interactive tutor for learning Claude Code concepts including MCP servers, skills, agents, and agentic workflows. Use when asking "how do I...", "what is...", or "explain..." questions about Claude Code. Provides hands-on exercises and demonstrations.
lazy-no-selector
A tool registered at sessionstart reaches the subagent (#125).
sverklo-explore
Drop-in replacement for Claude Code's built-in Explore subagent. Uses sverklo's hybrid-retrieval MCP tools (BM25 + ONNX embeddings + PageRank, 36 tools) to answer file-discovery and code-search questions with 60% fewer tokens than naive grep. Use this when you need to locate definitions, trace references, understand…