ci-failure-escalation

ci-failure-escalation is an agent for Claude Code from ivegamsft/basecoat. It costs 79 tokens per session (704 once invoked), scanned A, original, MIT.

A CI/CD monitor that counts repeated failures in one GitHub Actions job and stops deployments after a set threshold.

In plain words
What is it for?
Use it to watch a workflow job, open or update a blocker issue after consecutive failures, and gate deployment to the affected environment.
Why use it?
It prevents an ongoing broken build from reaching an environment and gives the team one blocking issue to track.

Agent for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter.

Good fit Use it to watch a workflow job, open or update a blocker issue after consecutive failures, and gate deployment to the affected environment.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/ivegamsft/basecoat/basecoat-60-workflow-ci-failure-escalation
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo
git clone --depth 1 https://github.com/ivegamsft/basecoat

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-failure-escalation

README.md
[![agentmods](https://agentmods.dev/badge/agents/ivegamsft/basecoat/basecoat-60-workflow-ci-failure-escalation/github.svg)](https://agentmods.dev/agents/ivegamsft/basecoat/basecoat-60-workflow-ci-failure-escalation)
Your own site
<a href="https://agentmods.dev/agents/ivegamsft/basecoat/basecoat-60-workflow-ci-failure-escalation"><img src="https://agentmods.dev/badge/agents/ivegamsft/basecoat/basecoat-60-workflow-ci-failure-escalation/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-failure-escalation

Your own site · 80×15
<a href="https://agentmods.dev/agents/ivegamsft/basecoat/basecoat-60-workflow-ci-failure-escalation"><img src="https://agentmods.dev/badge/agents/ivegamsft/basecoat/basecoat-60-workflow-ci-failure-escalation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 79 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 704 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 $0.00079 $0.00704
Opus 5 $0.00039 $0.00352
Sonnet 5 $0.00016 $0.00141
Haiku 4.5 $0.00008 $0.00070

Measured 4d ago against content hash d5c3b71c61bf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

ci-failure-escalation 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 4d 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.

agents/basecoat-60-workflow-ci-failure-escalation.agent.md · 43 lines

How it starts

The opening of the file, as written. The whole thing — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CI Failure Escalation Agent

Purpose: Monitors a GitHub Actions workflow job for consecutive failures, halts the line by opening a blocking issue and gating deployments past the configured threshold — the andon cord pattern. Complements self-healing-ci (automated remediation); this agent escalates when remediation isn't working.

Inputs

  • repo (required) — GitHub owner/repo slug
  • workflow_name (required) — workflow file/display name
  • job_name (required) — job within the workflow to monitor
  • failure_threshold (optional, default 3) — consecutive failures before escalating
  • environment (optional) — deployment environment to gate

Workflow

  1. Query recent runs — fetch the last failure_threshold + 2 runs of workflow_name, filter to job_name. Consult docs/reference/repo-pathways.md for a matching signature before opening a new blocking issue.
  2. Count consecutive failures — walk runs newest→oldest; stop at first success/skip.
  3. If consecutive failures ≥ threshold: a. Open or update a blocking issue keyed by a stable repo/workflow_name/job_name marker (not the failure count, so repeated failures update the issue instead of duplicating), label blocker, body with failure timeline, last error snippet, remediation — see template in detail file. b. Gate the environment (if provided): confirm custom_branch_policies: true first (only that mode can be halted); snapshot each policy's id/name/type; require explicit Tier-3 confirmation restating target/impact before deleting them (docs/reference/guardrails/tool-confirmation-policy.md); otherwise post manual gate instructions. c. Post a new failing check run referencing the halt (if permitted) linking the blocking issue.
  4. Below threshold: report count/margin; suggest self-healing-ci first for App Service/startup failures.
  5. On resolution — comment with summary, recreate the snapshotted policies (name/type; ids are new), confirm next run passes.

Read the full file on GitHub · 43 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. 4d ago Changed d5c3b71c61bf
  2. 6d ago First seen · 43 lines · 79 tokens per session scan A ed221898788f

Subscribe to this mod's changes

ci-failure-escalation is an agent published in the GitHub repository ivegamsft/basecoat (4 stars, last pushed yesterday), licensed MIT. It adds 79 tokens to every session and 704 once invoked, about $0.0004 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 2026-09-03.