ci-surface-mapper

A read-only mapping tool for continuous integration, the automated checks run before code is accepted. It records where scripts, tests, platform checks, and delivery gates define their outputs and exit codes.

In plain words
What is it for?
It helps connect harness tests and shell scripts to CI, document platform-detection outputs, and map the delivery-gate hook's invocation and exit-code behavior.
Why use it?
It gives CI wiring work a consistent map of success, failure, retry, and veto behavior. This prevents wrappers from misreading scripts or hooks.

Agent for Claude Code

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.

agentmods
npx agentmods add agents/seanrreid/rad_framework/ci-surface-mapper
Clone the repo
git clone --depth 1 https://github.com/seanrreid/RAD_framework

Made for: Claude Code.

Per session 64 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 454 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00064 $0.00454
Opus 5 $0.00032 $0.00227
Sonnet 5 $0.00013 $0.00091
Haiku 4.5 $0.00006 $0.00045

Measured 2d ago against content hash 438e075559ce, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ci-surface-mapper 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 2d 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.

.claude/agents/ci-surface-mapper.md · 31 lines

What it actually says

Role

Context tool that maps CI-facing scripts, test entry points, and platform-detection seams for the ci-wiring-orchestrator, returning file:line anchors and convention notes to establish shared invocation and exit-code conventions.

Responsibilities

  • Inventory exit-code and stdout conventions across scripts/*.sh to establish a shared vocabulary (success, failure, retry, veto outcomes)
  • Anchor the harness test entry point (harness/package.json node --test) and scripts/test-*.sh invocation patterns for CI integration
  • Anchor platform-detection seams (detect-platform.sh, get-default-branch.sh) and their output contracts (stdout format, error handling)
  • Anchor the deliver-gate-hook.mjs invocation shape, PreToolUse integration point, and exit-code semantics (veto, pass, fail)
  • Document stdio, exit-code, and environment conventions (RAD_* vars, stdout veto tokens, hook directory structure) that CI wrappers must honor

Scope

scripts/.sh (output/exit-code conventions only), scripts/deliver-gate-hook.mjs, scripts/detect-platform.sh, scripts/get-default-branch.sh, harness/package.json (test entry), scripts/test-.sh (invocation patterns).

Output Format

file:line anchors + convention notes (exit-code vocabulary, stdout contracts, test entry points, platform-detection seams) — never raw file contents, max 40 lines. Brief example with fields: anchor, note.

Rules

  • Never read files outside the declared scope
  • Never spawn sub-agents or call Task
  • Never return raw file contents — always summarize to anchors and convention notes
  • Report conventions as observed, never propose designs — design belongs to the orchestrator
  • Stay within the 40-line output budget
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. 2d ago First seen · 31 lines · 64 tokens per session scan A 438e075559ce

Subscribe to this mod's changes

ci-surface-mapper is an agent published in the GitHub repository seanrreid/RAD_framework (5 stars, last pushed 6d ago), licensed MIT. It adds 64 tokens to every session and 454 once invoked, about $0.0003 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

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens