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 skills add ai-analyst-lab/ai-analyst --skill triangulationgit clone --depth 1 https://github.com/ai-analyst-lab/ai-analystWrote 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/skills/ai-analyst-lab/ai-analyst/triangulation)<a href="https://agentmods.dev/skills/ai-analyst-lab/ai-analyst/triangulation"><img src="https://agentmods.dev/badge/skills/ai-analyst-lab/ai-analyst/triangulation/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/skills/ai-analyst-lab/ai-analyst/triangulation"><img src="https://agentmods.dev/badge/skills/ai-analyst-lab/ai-analyst/triangulation.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 | $0.00037 | $0.00497 |
| Opus 5.5 | $0.00015 | $0.00199 |
| Sonnet 5.5 | $0.00007 | $0.00099 |
| Haiku 4.5 | $0.00004 | $0.00050 |
Grade A, and why
triangulation 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 1mo 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 — 35 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Triangulate an analysis
Select paths deliberately
First determine what the available data can support. Choose paths that differ in method, source, population, assumptions, or counterfactual. Opening more sessions that repeat the same method is not meaningful triangulation.
Each path must work without seeing the other paths' conclusions. Record:
- path ID;
- method;
- source;
- population;
- assumptions;
- direction as
yes,no, orunclear; and - the evidence supporting that direction.
For a live analysis, use three paths unless the user requests another number. Inspect the available data first, then propose three methods that answer different parts of the decision and rely on meaningfully different assumptions. Aim for a 400-word proposal and never exceed 500 words. Keep each path narrow enough to complete with no more than two read-only queries and a narrative of no more than 250 words unless the user asks for a deeper analysis. Compact SQL and result tables do not count toward the narrative limit.
After the user approves the methods, run the three paths in fresh subagents in parallel. Give each subagent the complete original task and terminology constraints, its assigned method, the approved data source, the two-query and 250-word narrative limits, and the required output fields. Do not paraphrase or omit user constraints when delegating. Do not show one path another path's work.
Save each path separately under working/triangulation/<slug>/, then save a comparison that shows the method, question answered, assumptions, important evidence, direction, and limitations for every path.
Compare the paths
Use helpers.evals.triangulation.build_grid to assemble the comparison. Run each genuinely different path once. A second full round is not required. If one path is surprising or disputed, rerun only that path in a fresh context to determine whether the difference is run variation or a persistent methodological disagreement.
When paths disagree, locate the difference in their populations, assumptions, sources, or counterfactuals. Reconcile the difference only when the evidence supports it. Otherwise preserve the disagreement and escalate it.
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.
- 1mo ago Changed · +6 lines · -4 tokens per session 4a75e9a90f68
- 1mo ago First seen · 29 lines · 41 tokens per session scan A 28c306d62c3b
triangulation is a skill published in the GitHub repository ai-analyst-lab/ai-analyst (322 stars, last pushed 1mo ago), licensed MIT. It adds 37 tokens to every session and 497 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-12.
triangulation compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| triangulationai-analyst-lab/ai-analyst | Skill | 322 | 1mo ago | MIT | A | 37 | Claude Code |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |