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.
Borrowing it
Nothing to install: this file belongs to latitude-dev/latitude-llm. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/latitude-dev/latitude-llm/development/.agents/skills/gh-issue/SKILL.mdgit 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/gh-issue)<a href="https://agentmods.dev/skills/latitude-dev/latitude-llm/gh-issue"><img src="https://agentmods.dev/badge/skills/latitude-dev/latitude-llm/gh-issue.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 5.1 | $0.00037 | $0.01265 |
| Opus 5 | $0.00018 | $0.00633 |
| Sonnet 5 | $0.00007 | $0.00253 |
| Haiku 4.5 | $0.00004 | $0.00127 |
Grade A, and why
gh-issue 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 7d 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 — 212 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitHub Issue Creation
Create clear, actionable GitHub issues for bugs, features, and improvements. Issues are primarily consumed by LLMs, so optimize for agent readability and actionability.
When to Create an Issue
- Bugs discovered during development or testing
- Feature requests from product/design
- Technical debt or refactoring needs
- Schema changes requiring migrations
- Missing error handling, telemetry, or validation
- Architectural improvements
Required: Always Use the llm Label
Every issue MUST include the llm label. This ensures the issue appears in LLM-facing issue feeds and boards.
gh issue create --title "..." --label llm --body "..."
Issue Structure
Structure issues to help LLMs understand the problem and intended outcome without prescribing implementation details.
Template
## Problem
Clear, concise description of what is wrong or missing. One paragraph maximum.
## Impact
- Bullet points describing why this matters
- What breaks or what capability is missing
- User-facing consequences (if any)
## Proposed Solution (Optional)
High-level approach to fixing the problem. Do NOT include:
- Specific file paths
- Exact code snippets or function names
- Step-by-step implementation instructions
- Migration SQL (unless the issue IS the migration)
DO include:
- Which components/systems are involved
- Expected behavior after the fix
- Any constraints or requirements
## Acceptance Criteria
- [ ] Observable outcome 1
- [ ] Observable outcome 2
- [ ] Tests pass / typechecks pass
Example: Good Issue
## Problem
The outbox_events table has an aggregate_id column but no aggregate_type,
making it impossible to query events by entity type without parsing payloads.
## Impact
- Cannot build audit trails by entity type (e.g., "all organization events")
- Difficult to implement event replay for specific domains
- No way to validate event sources at the database level
## Proposed Solution
Add an aggregate_type column to outbox_events. Events should specify their
entity type ("organization", "user", "project"). System-level events without
a clear aggregate should use aggregate_type: "system" with a generated ID.
## Acceptance Criteria
- [ ] Migration adds aggregate_type column with index
- [ ] OutboxEventWriterShape updated to accept aggregateType
- [ ] All existing outboxWriter.write() calls updated
- [ ] Can query events by aggregate_type
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.
- 7d ago First seen · 212 lines · 37 tokens per session scan A e7e70b674bef
gh-issue is a skill published in the GitHub repository latitude-dev/latitude-llm (4,629 stars, last pushed yesterday), licensed MIT. It adds 37 tokens to every session and 1,265 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 2026-08-30.
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.