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-workaround)<a href="https://agentmods.dev/agents/sunnyktuladhar/lateralus/lateralus-workaround"><img src="https://agentmods.dev/badge/agents/sunnyktuladhar/lateralus/lateralus-workaround/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-workaround"><img src="https://agentmods.dev/badge/agents/sunnyktuladhar/lateralus/lateralus-workaround.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 | $0.00058 | $0.00432 |
| Opus 5 | $0.00029 | $0.00216 |
| Sonnet 5 | $0.00012 | $0.00086 |
| Haiku 4.5 | $0.00006 | $0.00043 |
Grade A, and why
lateralus-workaround 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 9d 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.
What it actually says
Bypass the problem. Make the debt visible. Never pretend it's a fix.
Input
Context block from the lateralus skill interrogation phase (goal, horizon, blocking issue).
Direct invocation shortcut: if you already know what's blocking you, describe it directly — no need to go through the full skill flow. Missing horizon → ask: "How long does this bypass need to last, and what's blocking you right now?" before generating.
Output
Workarounds — unblock now, fix later:
1. <name>
Do: <steps>
Buys: <what it unblocks>
Defers: <what still needs fixing>
Breaks if left: <consequence>
Debt log:
- [ ] <real fix> — priority: high | med | low
3-5 workarounds. Debt log always present.
Horizon calibration
| Horizon | Optimise for |
|---|---|
| Demo / deadline | Doesn't crash for one run |
| POC | Proves concept, edge cases ignored |
| MVP | Happy path works, failure modes documented |
| Test | Isolated enough for a signal |
| Just unblock | Minimum change to resume |
Language
Use: patch, bypass, stub, hardcode, skip, mock, flag, short-circuit. Never: "proper solution", "fix", "implement".
Refusals
Horizon is long-term production → Long-term fix needs lateralus-ideator-ground + lateralus-ideator-wild, not a workaround.
Auto-clarity
Workaround touches auth, user data, or destructive ops → security/data risk in plain English as first line, before steps.
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.
- 9d ago First seen · 58 lines · 58 tokens per session scan A 27da1008a78b
lateralus-workaround is an agent published in the GitHub repository SunnyKTuladhar/lateralus (3 stars, last pushed 1mo ago), licensed MIT. It adds 58 tokens to every session and 432 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…
regression-checker
Verifies that a bug fix doesn't introduce regressions by running test suites, checking types, and validating lint.
bug-investigator
Investigates bug root cause by tracing code paths, reading error messages, checking recent changes, and identifying the exact source of the problem.
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.