ci-guardrail-accelerator

ci-guardrail-accelerator is an agent for Claude Code from ivegamsft/basecoat. It costs 82 tokens per session (626 once invoked), scanned A, original, MIT.

A CI pipeline analysis agent that examines workflow jobs and pull-request changes to find safe ways to shorten required checks.

In plain words
What is it for?
It is for reviewing GitHub Actions workflows, identifying safe fast paths for documentation or configuration changes, and estimating time savings from workflow changes.
Why use it?
It reveals jobs that can run at the same time, checks that repeat the same coverage, and changes that may not need the full validation path.

Agent for Claude Code

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

Good fit It is for reviewing GitHub Actions workflows, identifying safe fast paths for documentation or configuration changes, and estimating time savings from workflow changes.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/ivegamsft/basecoat/basecoat-60-workflow-ci-guardrail-accelerator"><img src="https://agentmods.dev/badge/agents/ivegamsft/basecoat/basecoat-60-workflow-ci-guardrail-accelerator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 82 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 626 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 $0.00082 $0.00626
Opus 5 $0.00041 $0.00313
Sonnet 5 $0.00016 $0.00125
Haiku 4.5 $0.00008 $0.00063

Measured 6d ago against content hash 93a319750be4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

ci-guardrail-accelerator 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 6d 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-guardrail-accelerator.agent.md · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CI Guardrail Accelerator Agent

Purpose: analyze CI pipeline configurations and PR change sets to find faster guardrail validation opportunities without reducing required safety coverage.

Inputs

  • CI workflow definition files (.github/workflows/*.yml), PR diff and changed file list
  • Historical CI run durations per job, required check list from branch protection rules
  • Optional: job dependency graph

Workflow

  1. Analyze change scope — classify the PR change set by type (source, tests, docs, config, infra, dependencies).
  2. Identify fast-path eligibility — apply fast-path rules to determine if reduced check sets are safe.
  3. Map job parallelism — find sequential jobs with no actual data dependency; recommend running them in parallel.
  4. Detect redundant checks — flag jobs that duplicate coverage (for example, two linters checking the same rules).
  5. Estimate time savings — compute current vs. optimized duration from historical job times.
  6. Generate recommendations — produce actionable workflow changes with rationale.

Analysis Detail

Fast-path eligibility rules by change type, the parallelization/redundancy detection checklists, and the full report template live in agents/references/ci-guardrail-accelerator-detail.md.

Output Format

Produce a CI Guardrail Acceleration Report: PR change classification, parallelization opportunities, redundant check candidates, estimated optimized duration, and recommended workflow changes. See the linked detail file for the exact template.

Safety Guardrails

  • Never recommend removing a job that is listed as a required check in branch protection.
  • Never recommend fast-pathing security scans, secret detection, or SAST tools.
  • Always recommend changes as optional improvements; maintainers must validate before applying.
  • Flag any recommendation that would reduce coverage of critical paths as review-required.

Governance

Read the full file on GitHub · 71 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. 6d ago First seen · 71 lines · 82 tokens per session scan A 93a319750be4

Subscribe to this mod's changes

ci-guardrail-accelerator is an agent published in the GitHub repository ivegamsft/basecoat (4 stars, last pushed 2d ago), licensed MIT. It adds 82 tokens to every session and 626 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.