Latitude is an open-source platform for monitoring AI agents by collecting execution traces, grouping failures, dispatching coding agents to make fixes, and replaying failures to verify them. Teams use it to observe agent behavior, investigate errors, and monitor whether fixes prevent regressions. The catalogue entries include skills, instructions, and an MCP server for working with Latitude.
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 skills/latitude-dev/latitude-llm/analyze-problemnpx skills add latitude-dev/latitude-llm --skill analyze-problemgit clone --depth 1 https://github.com/latitude-dev/latitude-llmWrote 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/latitude-dev/latitude-llm/analyze-problem)<a href="https://agentmods.dev/skills/latitude-dev/latitude-llm/analyze-problem"><img src="https://agentmods.dev/badge/skills/latitude-dev/latitude-llm/analyze-problem.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 | $0.00027 | $0.00320 |
| Opus 5 | $0.00014 | $0.00160 |
| Sonnet 5 | $0.00005 | $0.00064 |
| Haiku 4.5 | $0.00003 | $0.00032 |
Grade A, and why
analyze-problem 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.
What it actually says
Read the provided bug report/issue/task.
Then thoroughly investigate the codebase to understand the relevant context:
- Find the entry points involved (routes/handlers/jobs/commands) and trace the execution path that leads to the reported behavior.
- Identify the data flow and state involved (inputs, validation, persistence, caching, permissions, feature flags, side effects).
- Locate the expected behavior (specs/tests/docs) and compare it to the actual behavior in code.
- If the report includes steps to reproduce, map each step to the corresponding code path and decision points.
- Consider common edge cases (null/empty values, timing/race conditions, retries, idempotency, pagination, timezones, auth, stale cache).
Deliverable: Explain, in your own words:
- What you believe the issue is (observable behavior + when it happens),
- Why you believe it is happening (root cause and the specific assumption/logic that breaks),
- How you would fix it (proposed approach and what behavior/logic should change),
- What you would verify (minimal set of checks/tests/logs to confirm the fix and prevent regressions).
Constraints:
- Do not apply any changes automatically.
- Avoid listing files/components/services unless strictly necessary to support the explanation.
- If the codebase does not contain enough context to be confident, explicitly say what’s missing and what evidence would confirm the hypothesis.
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 · 30 lines · 27 tokens per session scan A 8dcc4dfc7703
analyze-problem is a skill published in the GitHub repository latitude-dev/latitude-llm (4,626 stars, last pushed today), licensed MIT. It adds 27 tokens to every session and 320 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
trulens-evaluation-setup
Configure feedback functions and selectors for TruLens evaluations.
trulens-instrumentation
Instrument LLM apps with TruLens OTEL-based tracing - from setup to debugging and optimization.
trulens-evaluation-workflow
Systematically evaluate your LLM application with TruLens.
trulens-notebook-execution
Execute and display Jupyter notebooks for TruLens demos and quickstarts.
trulens-blocking-guardrails
Configure and use feedback functions as runtime blocking guardrails.
trulens-dataset-curation
Create and curate evaluation datasets with ground truth for TruLens.