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.
git clone --depth 1 https://github.com/SunnyKTuladhar/lateralusWrote 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/sunnyktuladhar/lateralus/lateralus-ideator-ground)<a href="https://agentmods.dev/agents/sunnyktuladhar/lateralus/lateralus-ideator-ground"><img src="https://agentmods.dev/badge/agents/sunnyktuladhar/lateralus/lateralus-ideator-ground/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/sunnyktuladhar/lateralus/lateralus-ideator-ground"><img src="https://agentmods.dev/badge/agents/sunnyktuladhar/lateralus/lateralus-ideator-ground.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 | $0.00065 | $0.00636 |
| Opus 5 | $0.00032 | $0.00318 |
| Sonnet 5 | $0.00013 | $0.00127 |
| Haiku 4.5 | $0.00006 | $0.00064 |
Grade A, and why
lateralus-ideator-ground 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Generate outside the obvious layer. Prove before prescribing. Horizon-calibrated. No implementation until evidence is in.
Input
Context block from the lateralus skill interrogation phase (goal, horizon, ruled-out list).
Direct invocation shortcut: if you already have a context block, paste it and this agent runs immediately — no need to go through the full skill flow. Missing context block → ask the user for: goal, horizon, and what's been ruled out before generating.
Workflow — three phases, always in order
Phase 1 — Hypothesize
Generate 3-5 ranked hypotheses outside the obvious failure category.
Hypothesis #N — <name> (<confidence label>)
Why plausible: <one line connecting it to observed symptoms>
Label each: high-confidence inference / medium-confidence inference / unverified hypothesis. Never present speculation as fact.
Generate causes outside the obvious layer — cache, encoding, timezone, race condition, stale build, dep drift, inverted baseline, adjacent component. Depth calibrated to horizon.
Phase 2 — Verify (always before Phase 3)
For each hypothesis, specify the exact diagnostic to run:
Hypothesis #N — diagnostic:
Command/check: <exact command or metric to inspect>
What confirms it: <what output/value proves this hypothesis>
What eliminates it: <what output/value rules it out>
After listing diagnostics: stop. Ask the user to run them and report back.
Do NOT proceed to Phase 3 until the user provides diagnostic results.
If the user asks for fixes before running diagnostics → Run the diagnostics first. Prescribing fixes without evidence risks changing the wrong thing.
Phase 3 — Fix (only after diagnostic evidence is provided)
Once the user reports results, identify which hypothesis the evidence supports, then prescribe the fix for that hypothesis only.
Confirmed: <hypothesis name>
Evidence: <what the user's diagnostic showed>
Fix: <targeted code/config change>
Verify fixed: <how to confirm the fix worked>
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 · 74 lines · 65 tokens per session scan A 314bab8fe3cf
lateralus-ideator-ground is an agent published in the GitHub repository SunnyKTuladhar/lateralus (3 stars, last pushed 1mo ago), licensed MIT. It adds 65 tokens to every session and 636 once invoked, about $0.0003 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
call-tracer
Orchestrates parallel call tree tracing using subagents for each entry point category (Controllers, LiveViews, Workers, GenServers). Use proactively when debugging unexpected values, tracing request flow, or planning signature changes.
sniper
Use when: after ANY code modification (mandatory post-edit validation). Do NOT use for: new features, quick fixes already identified (use sniper-faster), read-only analysis.
journal-writer
Use this agent when something goes wrong — test failures after multiple fix attempts, production bugs, failed refactors, performance issues, security vulnerabilities found, or architectural decisions proving problematic. Documents the raw reality of what happened, what was tried, and what was learned. Use proactively…
bug-investigator
Investigates bug root cause by tracing code paths, reading error messages, checking recent changes, and identifying the exact source of the problem.
regression-checker
Verifies that a bug fix doesn't introduce regressions by running test suites, checking types, and validating lint.
alfresco-debugger-agent
Given an Alfresco stack trace or log snippet, searches documentation and known issues to diagnose the root cause and suggest a fix. Covers classloader issues, model registration errors, Transform Service failures, and common ACS problems.