dogma: Agent for Claude Code

.github/agents/ci-monitor.agent.md

CI Monitor is an agent for Claude Code from EndogenAI/dogma. It costs 33 tokens per session (1,421 once invoked), scanned A, original, Apache-2.0.

An agent that reviews GitHub Actions, the service that runs automated checks for a repository. It examines past CI runs to find repeated failures, unreliable tests, and slow workflow steps.

In plain words
What is it for?
It is for analyzing CI history, investigating flaky tests, identifying slow jobs, and suggesting fixes for the GitHub Actions pipeline.
Why use it?
It helps teams spot recurring problems before they block pull requests or consume developers’ time.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: mentions AGENTS.md.

This is EndogenAI/dogma's own configuration. It tells Claude Code how to work on dogma 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 dogma configures →

Reuse

Borrowing it

Nothing to install: this file belongs to EndogenAI/dogma. 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/EndogenAI/dogma/main/.github/agents/ci-monitor.agent.md
Clone the repo
git clone --depth 1 https://github.com/EndogenAI/dogma

Made for: Claude Code.

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 Monitor

README.md
[![agentmods](https://agentmods.dev/badge/agents/endogenai/dogma/ci-monitor/github.svg)](https://agentmods.dev/agents/endogenai/dogma/ci-monitor)
Your own site
<a href="https://agentmods.dev/agents/endogenai/dogma/ci-monitor"><img src="https://agentmods.dev/badge/agents/endogenai/dogma/ci-monitor/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 Monitor

Your own site · 80×15
<a href="https://agentmods.dev/agents/endogenai/dogma/ci-monitor"><img src="https://agentmods.dev/badge/agents/endogenai/dogma/ci-monitor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 33 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,421 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.
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 $0.00033 $0.01421
Opus 5 $0.00016 $0.00711
Sonnet 5 $0.00007 $0.00284
Haiku 4.5 $0.00003 $0.00142

Measured 11d ago against content hash 89fc05467cd6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

CI Monitor 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 11d 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.

.github/agents/ci-monitor.agent.md · 179 lines

How it starts

The opening of the file, as written. The whole thing — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the CI Monitor for the EndogenAI Workflows project. Your mandate is to watch the GitHub Actions CI run history, identify recurring failure patterns, triage flaky tests, surface the slowest workflow steps, and produce actionable fix recommendations — before failures block PRs or waste developer time.


Beliefs & Context

  1. .github/workflows/ — the CI workflow definitions.
  2. docs/toolchain/gh.md — canonical gh run command patterns; consult before running any gh run commands.
  3. pyproject.toml — test configuration; markers, coverage settings.
  4. .lycheeignore — known dead-link exclusions (lychee failures are documented here).
  5. The active session scratchpad (.tmp/<branch>/<date>.md) — read before acting.
  6. AGENTS.md — guiding constraints that govern all agent behavior in this repository.

Follows the programmatic-first principle: tasks performed twice interactively must be encoded as scripts.


Workflow & Intentions

1. Orient

Read the CI workflow files to understand what jobs exist and what they do.

ls .github/workflows/
cat .github/workflows/tests.yml

2. Recent Run History

# Last 20 runs across all workflows
gh run list --limit 20 --json databaseId,conclusion,workflowName,headBranch,createdAt

# Failed runs only
gh run list --limit 20 --status failure --json databaseId,conclusion,workflowName,headBranch,createdAt

3. Failure Pattern Analysis

For each failed run, retrieve the failure details:

gh run view <run-id> --log-failed 2>&1 | head -100

Categorize failures:

  • Lychee dead links — add to .lycheeignore with reason comment
  • Ruff lint failures — code introduced after last ruff check
  • Ruff format failures — code introduced without ruff format
  • Pytest failures — test regression, flaky test, or new code without tests
  • uv sync failures — dependency declaration vs. lock inconsistency
  • validate_synthesis failures — D4 heading gaps in research docs

Read the full file on GitHub · 179 lines

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. 11d ago First seen · 179 lines · 33 tokens per session scan A 89fc05467cd6

Subscribe to this mod's changes

CI Monitor is an agent published in the GitHub repository EndogenAI/dogma (2 stars, last pushed 17d ago), licensed Apache-2.0. It adds 33 tokens to every session and 1,421 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 2026-08-31.

Related

Other agents, from other repositories

devops

CI/CD pipelines, build automation, and pipeline optimization. Use for setting up and maintaining build systems, GitHub Actions, and deployment workflows.

AgentWorkforce/relay · 31 tokens

infra-author

Use when writing or modifying IaC, containers, CI/CD manifests, or deployment configuration. Reads tech stack and security boundaries from {{PROJECTDIR}}/.codearbiter/.

arbiterForge/codeArbiter · 37 tokens

devops-engineer

Connects development and IT operations to automate software deployment and manage infrastructure — CI/CD, IaC, releases, and environment reliability.

VictorTomaili/agent-cli · 31 tokens

pact-researcher

Use proactively when the main conversation is about to write code that uses a package, library, or API it hasn't verified this session. Also invoke when building a new service, implementing security/crypto patterns, or encountering unexpected behavior from a dependency. Checks existing PACT knowledge files first…

jonathanmr22/pact · 81 tokens

pact-reviewer

Use proactively before committing feature work or multi-file changes (3+ files), or when the main conversation says a task is "done", "finished", "ready to commit", or "looks good". Skip for trivial commits (typo fixes, version bumps, single-line config changes). Runs PACT's governance checklist in an isolated context…

jonathanmr22/pact · 89 tokens

pact-tracer

Use proactively before editing files that appear in SYSTEMMAP.yaml, feature flow docs, or any file with more than 3 downstream dependents. Also invoke when the main conversation is about to change a database table, service, state management class, or shared utility. Traces dependency chains and returns a concrete…

jonathanmr22/pact · 80 tokens