latitude-llm: Skill for Claude Code

.agents/skills/ci-watchdog/SKILL.md

ci-watchdog is a skill for Claude Code, Codex from latitude-dev/latitude-llm. It costs 155 tokens per session (1,541 once invoked), scanned A, original, MIT.

A monitor for GitHub pull-request checks, the automated tests and quality checks that run before code is merged.

In plain words
What is it for?
Use it to watch a pull request, diagnose type or lint errors and other failures, fix the code, and push the resulting changes.
Why use it?
It helps find failing checks, investigate their logs, apply fixes, and repeat the process until the checks pass.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is latitude-dev/latitude-llm's own configuration. It tells Claude Code and Codex how to work on latitude-llm itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything latitude-llm configures →

About the project

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.

latitude-dev/latitude-llm · 4,632 stars · on GitHub · latitude.so

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/latitude-dev/latitude-llm/development/.agents/skills/ci-watchdog/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/latitude-dev/latitude-llm

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for ci-watchdog

README.md
[![agentmods](https://agentmods.dev/badge/skills/latitude-dev/latitude-llm/ci-watchdog/github.svg)](https://agentmods.dev/skills/latitude-dev/latitude-llm/ci-watchdog)
Your own site
<a href="https://agentmods.dev/skills/latitude-dev/latitude-llm/ci-watchdog"><img src="https://agentmods.dev/badge/skills/latitude-dev/latitude-llm/ci-watchdog/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.

agentmods 80×15 button for ci-watchdog

Your own site · 80×15
<a href="https://agentmods.dev/skills/latitude-dev/latitude-llm/ci-watchdog"><img src="https://agentmods.dev/badge/skills/latitude-dev/latitude-llm/ci-watchdog.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 155 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,541 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00155 $0.01541
Opus 5 $0.00077 $0.00771
Sonnet 5 $0.00031 $0.00308
Haiku 4.5 $0.00015 $0.00154

Measured 9d ago against content hash 457b78b4a6ed, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

ci-watchdog 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.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/parse_failures.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

.agents/skills/ci-watchdog/SKILL.md · 248 lines

How it starts

The opening of the file, as written. The whole thing — 248 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CI Watchdog

Monitor a GitHub PR's CI checks continuously, automatically fix failures, and loop until everything passes.

Quick Start

# Watch current PR until all checks pass (auto-fix enabled)
gh pr checks --watch --fail-fast

# Watch with auto-fix loop
ci-watchdog --fix --loop

Core Workflow

The CI watchdog follows this loop:

  1. Monitor - Watch PR checks until they complete or fail
  2. Detect - Identify which checks failed
  3. Diagnose - Fetch logs and understand the failure
  4. Fix - Apply appropriate fixes to the codebase
  5. Commit - Stage, commit, and push fixes
  6. Repeat - Go back to monitoring until all pass

Usage Patterns

Basic Watch Mode

Just monitor without fixing:

gh pr checks --watch

Auto-Fix Loop (Recommended)

Monitor and automatically fix issues:

LOOP:
  1. Run: gh pr checks --watch --fail-fast
  2. IF checks pass → DONE
  3. IF checks fail:
     a. Identify failed check names
     b. Fetch logs: gh run view <run-id> --log-failed
     c. Analyze error patterns
     d. Apply fixes to codebase
     e. Commit and push
     f. GOTO LOOP

Failure Patterns & Fixes

Type Errors / Lint Errors

Detection: typecheck, lint, check, pyright, tsgo failures

Common fixes:

  • Read the specific file and line from error output
  • Fix the type mismatch or syntax error
  • Remove references to deleted/renamed properties
  • Add missing imports or type annotations

Example flow:

# Check failed with pyright errors in file X
python -m pyright src/path/to/file.py 2>&1 | head -30
# → Shows specific line/column errors
# → Fix the issues
# → Commit and push

Test Failures

Detection: test check failures

Common fixes:

  • Read the failing test file
  • Update test assertions to match new behavior
  • Remove obsolete test cases
  • Fix test data/setup issues

Example flow:

# Tests failed
# Read the test file mentioned in error
# Update assertions or remove obsolete tests
# Commit and push

Read the full file on GitHub · 248 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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.

  1. 9d ago First seen · 248 lines · 155 tokens per session scan A 457b78b4a6ed

Subscribe to this mod's changes

ci-watchdog is a skill published in the GitHub repository latitude-dev/latitude-llm (4,632 stars, last pushed today), licensed MIT. It adds 155 tokens to every session and 1,541 once invoked, about $0.0008 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.