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/agentation-watch-mode/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/agentation-watch-mode)<a href="https://agentmods.dev/skills/latitude-dev/latitude-llm/agentation-watch-mode"><img src="https://agentmods.dev/badge/skills/latitude-dev/latitude-llm/agentation-watch-mode/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/latitude-dev/latitude-llm/agentation-watch-mode"><img src="https://agentmods.dev/badge/skills/latitude-dev/latitude-llm/agentation-watch-mode.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00051 | $0.00364 |
| Opus 5 | $0.00026 | $0.00182 |
| Sonnet 5 | $0.00010 | $0.00073 |
| Haiku 4.5 | $0.00005 | $0.00036 |
Grade A, and why
agentation-watch-mode 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
Agentation watch mode
When to use: The user says watch mode, wants continuous Agentation feedback handling, or asks you to keep watching annotations and applying fixes as new feedback arrives.
Goal
Stay in a watch loop so the user can annotate in the browser and have those annotations processed continuously.
Workflow
- Start a watch loop with
agentation_agentation_watch_annotations. - For each returned annotation:
- Call
agentation_agentation_acknowledgeimmediately so the user can see you picked it up. - Read any extra session context you need.
- Make the requested fix.
- Call
agentation_agentation_resolvewith a short summary of what changed.
- Call
- After the batch is done, call
agentation_agentation_watch_annotationsagain. - Continue until the user says stop or the watch call times out.
Defaults
- If the user gives a session ID, watch that session.
- If they do not, watch all sessions.
- Use a short batching window so nearby annotations are grouped together.
- Use a reasonable timeout and report when it expires.
Handling ambiguous feedback
- If an annotation is unclear, reply on the thread with a short clarifying question before making speculative changes.
- If you cannot complete the fix safely, leave the annotation open and explain the blocker in a reply.
Response style
- Keep progress updates brief.
- In each resolve summary, state what you changed, not just that it is done.
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 · 41 lines · 51 tokens per session scan A 4a8a3219a34d
agentation-watch-mode is a skill published in the GitHub repository latitude-dev/latitude-llm (4,632 stars, last pushed yesterday), licensed MIT. It adds 51 tokens to every session and 364 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 2026-08-30.
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-notebook-execution
Execute and display Jupyter notebooks for TruLens demos and quickstarts.
trulens-evaluation-workflow
Systematically evaluate your LLM application with TruLens.
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.