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/production-release/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/production-release)<a href="https://agentmods.dev/skills/latitude-dev/latitude-llm/production-release"><img src="https://agentmods.dev/badge/skills/latitude-dev/latitude-llm/production-release/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/production-release"><img src="https://agentmods.dev/badge/skills/latitude-dev/latitude-llm/production-release.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 | $0.00040 | $0.01260 |
| Opus 5 | $0.00020 | $0.00630 |
| Sonnet 5 | $0.00008 | $0.00252 |
| Haiku 4.5 | $0.00004 | $0.00126 |
Grade A, and why
production-release 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.
How it starts
The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Production release
Use this skill when preparing a production deployment. If the skill is invoked
without additional context or constraints, assume the user wants the default
patch production release flow: update CHANGELOG.md, bump the Helm chart
version, commit both as release: vX.Y.Z, push it to origin/development, and
run the production tag script for the next patch version. Production deploys are triggered by pushing a
vX.Y.Z tag; the changelog is updated at release time as a human-readable diff
of the code being pushed to production since the previous production deploy,
focused on the major aspects rather than every commit.
Release invariants
developmentis trunk and deploys to staging by default.- Production is triggered only by pushing a
vX.Y.Ztag that points at the latestorigin/developmentcommit. - Do not promote by merging
developmentintomain. - Do not tag unreleased local-only commits. The release commit, including any
changelog update, must be pushed to
origin/developmentbefore tagging. - The changelog release commit message must always have the exact shape
release: vX.Y.Z, for examplerelease: v1.2.3. - Update
CHANGELOG.mdduring release preparation, before running the command that pushes the production tag. - The Helm chart (
charts/latitude/Chart.yaml) tracks the Latitude release: set bothversionandappVersiontoX.Y.Z(no leadingv) in the samerelease: vX.Y.Zcommit as the changelog.scripts/release.shrefuses to tag a release whose chart version does not match.
Default behavior when no extra context is given
When the user only invokes this skill (or says something like "production release") without specifying a version, dry run, changelog-only update, or other constraint:
- Treat it as approval to perform the full patch release workflow.
- Determine the next patch version from the latest
vX.Y.Ztag. - Update
CHANGELOG.mdfor that next patch version using the production diff. - Set
versionandappVersionincharts/latitude/Chart.yamlto the newX.Y.Z. - Commit both with the exact message
release: vX.Y.Zand push toorigin/development. - Run
scripts/release.sh --yes(without an explicit version) so it tags the latestorigin/developmentcommit with the next patch version. The--yesflag is required when running non-interactively (agent or CI): the script's confirmation prompt cannot be answered without a terminal, and without--yesit exits with an error rather than tagging.
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 · 110 lines · 40 tokens per session scan A c701ec758acd
production-release is a skill published in the GitHub repository latitude-dev/latitude-llm (4,632 stars, last pushed today), licensed MIT. It adds 40 tokens to every session and 1,260 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
release-announcement
Draft or revise ax release announcements and website changelog pages. Triggers when the user says "write release notes", "draft release announcement", "prepare changelog", "release page", "version page", "what changed in vX.Y.Z", "generate announcement for vX.Y.Z", or asks for a release narrative. Uses Release Please…
release-announcement
Write a release announcement — changelog, blog post, in-app note, or social post — that leads with user impact, names the audience, and includes upgrade/migration steps without filler.
multi-agent-release-manager
Cleans up the workspace, formats code, runs presubmit checks, and uploads CLs to Gerrit.
release-notes
Generate user-facing release notes from tickets, PRDs, or changelogs. Creates clear, engaging summaries organized by category (new features, improvements, fixes). Use when writing release notes, creating changelogs, announcing product updates, or summarizing what shipped.
pack-submit
Package one of this agent's own skills as a standalone community pack and submit it to the aeon registry as a PR.
changelog-composer
Generates structured changelogs and release notes from git history and PRs, classifying breaking changes, features, fixes, performance, docs. Triggers on: "generate changelog", "write release notes", "what changed since", "prepare release", "release notes for", "diff since tag".