integrity-surface-mapper

A read-only mapping tool for the approval gate, approval-event format, plan fingerprint calculation, approval provenance, and repository-sync signals. It returns file locations and event-shape notes rather than source contents.

In plain words
What is it for?
Use it before changing checks related to approval records, signed plan fingerprints, approval history, gate folding, or synchronization errors from Git.
Why use it?
It provides the exact code and data structures needed to work safely on integrity checks. It also clarifies proxy approvals and which ownership events are excluded from gate decisions.

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

Made for: Claude Code.

Per session 70 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 504 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 $0.00070 $0.00504
Opus 5 $0.00035 $0.00252
Sonnet 5 $0.00014 $0.00101
Haiku 4.5 $0.00007 $0.00050

Measured 2d ago against content hash 430cdd70b450, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

integrity-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/integrity-surface-mapper.md · 32 lines

What it actually says

Role

Context tool that maps the gate fold entry points, approved-event schema, fingerprint computation inputs, and git-sync divergence signals—returning bounded anchors and shape notes only.

Responsibilities

  • Anchor gate fold entry points in harness/gates.js that read approved-event fields (email, timestamp, signature, fingerprint)
  • Anchor approved-event schema definition in harness/events.js, including proxy fields (recordedBy, on-behalf-of) and signature computation inputs
  • Anchor recordApproval invocation in harness/adapters/git-state-store.js and provenance-freezing logic (when and what is signed)
  • Anchor fingerprint computation inputs in harness/plan-fingerprint.js (plan content, author, timestamp) and hash algorithm
  • Anchor event types deliberately excluded from gate fold (owner-claimed, owner-released, architecture-approved) and why
  • Anchor git-sync.sh divergence exit-code vocabulary (e.g., exit 20 for owner-claimed, exit 21 for owner-released)

Scope

harness/gates.js, harness/events.js (schema + fold exclusions), harness/plan-fingerprint.js, harness/adapters/git-state-store.js (recordApproval, proxy fields), scripts/git-sync.sh (divergence exit codes), .agents/state/*/events.jsonl (shape samples only).

Output Format

file:line anchors + event/fingerprint-shape notes—approved-event fields (email, timestamp, signature, recordedBy, on-behalf-of), fingerprint computation inputs (plan hash algorithm, author freeze, timestamp freeze), fold-excluded event types (owner-claimed, owner-released, architecture-approved), divergence signal vocabulary—never raw file contents, max 40 lines.

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 shape notes
  • Sample events.jsonl files for record shape only—never enumerate or quote full logs
  • 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 · 32 lines · 70 tokens per session scan A 430cdd70b450

Subscribe to this mod's changes

integrity-surface-mapper is an agent published in the GitHub repository seanrreid/RAD_framework (5 stars, last pushed 7d ago), licensed MIT. It adds 70 tokens to every session and 504 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.