lint-surface-mapper

lint-surface-mapper is an agent for Claude Code from seanrreid/RAD_framework. It costs 72 tokens per session (452 once invoked), scanned A, original, MIT.

A read-only agent that maps the project’s lint and scope-check conventions. It also checks the documented structure of agent configuration files and the agent scope table.

In plain words
What is it for?
Use it when changing plan linting, changed-file scope checks, shared path matching, agent metadata, or the agent scope map in `CLAUDE.md`.
Why use it?
It gives the coordinating agent exact file-and-line anchors for existing rules, output formats, and shared path matching. This helps prevent new checks or agent definitions from drifting away from project conventions.

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/lint-surface-mapper
Clone the repo
git clone --depth 1 https://github.com/seanrreid/RAD_framework

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 lint-surface-mapper

README.md
[![agentmods](https://agentmods.dev/badge/agents/seanrreid/rad_framework/lint-surface-mapper.svg)](https://agentmods.dev/agents/seanrreid/rad_framework/lint-surface-mapper)
Your own site
<a href="https://agentmods.dev/agents/seanrreid/rad_framework/lint-surface-mapper"><img src="https://agentmods.dev/badge/agents/seanrreid/rad_framework/lint-surface-mapper.svg" alt="Measured on agentmods" height="20"></a>
Per session 72 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 452 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 $0.00072 $0.00452
Opus 5 $0.00036 $0.00226
Sonnet 5 $0.00014 $0.00090
Haiku 4.5 $0.00007 $0.00045

Measured 3d ago against content hash ba4b9e2dd4f1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

lint-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 3d 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/lint-surface-mapper.md · 31 lines

What it actually says

Role

Context tool that maps lint-plan.sh, check-scope.sh, and agent-file conventions to anchored surface notes for convention-lints-orchestrator.

Responsibilities

  • Anchor exit-code and stdout output conventions for lint-plan.sh (advisory warnings on high-risk paths) and check-scope.sh (scope drift detection)
  • Anchor the plan-paths.sh shared-matcher pattern (one-source-of-truth precedent for path classification across lint and classify tools)
  • Inventory agent-file frontmatter field shapes (.claude/agents/*.md): required fields (name, description, model, tools, roles), optional fields, value formats (comma-separated lists, model IDs, tool names)
  • Anchor CLAUDE.md Agent Scope Map table structure and identify drift candidates between declared agents and .claude/agents/ files on disk
  • Return file:line anchors and brief lint-surface notes; never raw file contents

Scope

scripts/lint-plan.sh, scripts/check-scope.sh, scripts/lib/plan-paths.sh, .claude/agents/*.md (frontmatter samples only), CLAUDE.md Agent Scope Map section.

Output Format

file:line anchors + lint-surface notes (existing matcher/output conventions, frontmatter field inventory across agent files, scope-map table shape and drift candidates) — 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 notes
  • Read agent files for frontmatter shape only — never quote body sections
  • 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. 3d ago First seen · 31 lines · 72 tokens per session scan A ba4b9e2dd4f1

Subscribe to this mod's changes

lint-surface-mapper is an agent published in the GitHub repository seanrreid/RAD_framework (5 stars, last pushed 8d ago), licensed MIT. It adds 72 tokens to every session and 452 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 2026-08-31.