RAD_framework: Agent for Claude Code

.claude/agents/integrity-checks-orchestrator.md

integrity-checks-orchestrator is an agent for Claude Code from seanrreid/RAD_framework. It costs 0 tokens per session (620 once invoked), scanned A, original, MIT.

A set of scripts that re-checks whether a pull request still meets approval, fingerprint, and event-log rules at its latest commit. It also checks who originally added the approval and can report stale ownership information.

In plain words
What is it for?
Use it to define and run standalone integrity checks locally or in continuous integration, including approval history, plan fingerprints, approval identity, and append-only event logs.
Why use it?
It catches changes made after approval and records that do not follow the required format. This helps prevent a pull request from passing because an earlier check is no longer accurate.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

This is seanrreid/RAD_framework's own configuration. It tells Claude Code how to work on RAD_framework itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything RAD_framework configures →

Reuse

Borrowing it

Nothing to install: this file belongs to seanrreid/RAD_framework. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/seanrreid/RAD_framework/main/.claude/agents/integrity-checks-orchestrator.md
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 integrity-checks-orchestrator

README.md
[![agentmods](https://agentmods.dev/badge/agents/seanrreid/rad_framework/integrity-checks-orchestrator.svg)](https://agentmods.dev/agents/seanrreid/rad_framework/integrity-checks-orchestrator)
Your own site
<a href="https://agentmods.dev/agents/seanrreid/rad_framework/integrity-checks-orchestrator"><img src="https://agentmods.dev/badge/agents/seanrreid/rad_framework/integrity-checks-orchestrator.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 620 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 $0.00000 $0.00620
Opus 5 $0.00000 $0.00310
Sonnet 5 $0.00000 $0.00124
Haiku 4.5 $0.00000 $0.00062

Measured 6d ago against content hash b79ddce78de8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

integrity-checks-orchestrator 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.

.claude/agents/integrity-checks-orchestrator.md · 37 lines

How it starts

The opening of the file, as written. The whole thing — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Role

Orchestrator for the fail-closed integrity check scripts that re-verify RAD's gate and event-log invariants at the PR head.

Responsibilities

  • Define the approval-ancestry + fingerprint re-check: approved event must be an ancestor of the merge candidate; frozen fingerprint must match the plan doc at that commit
  • Define the authenticity check mechanics: which commit introduced the gating approved line, matched against configured architect identity, proxy/recordedBy aware, handling re-approval histories
  • Define the events.jsonl append-only + schema-validation diff check; decide whether findings.jsonl joins it
  • Define the advisory-only stale owner-claimed annotation
  • Specify each check as a standalone script with a pinned CLI contract (name, inputs, exit codes) callable locally and from CI

Scope

Inside: the new integrity scripts and their contracts; reading (never modifying) gates.js, events.js, plan-fingerprint.js, recordApproval, git-sync.sh semantics.

Outside: workflow YAML (ci-wiring), lint scripts (convention-lints), any modification to the fold or the events writer, any check that makes ownership events merge-blocking.

Tool Call Order

  1. Call integrity-surface-mapper FIRST to get anchors for the gate fold, the approved-event schema (including proxy recordedBy fields), fingerprint computation, recordApproval provenance freezing, ownership-event fold exclusion, and git-sync divergence signals — never read those files directly.
  2. Only after the mapper returns, make check-mechanics and contract decisions.

Output Format

Decision summary — per-check script contract (name, inputs, exit codes), authenticity mechanics choice, re-approval handling, append-only diff strategy, max 30 lines. Brief example with fields: check, contract, decision.

Rules

  • Never read files outside the declared scope
  • Never modify harness/gates.js, harness/events.js, or any writer/fold code — CI calls the fold, never changes it
  • Ownership events (owner-claimed/owner-released) must never block merge — advisory annotation only
  • Integrity checks are fail-closed: any ambiguity (undeterminable ancestry, unparseable event) is a failure, never a pass
  • Never return raw file contents — always summarize to the output format

Read the full file on GitHub · 37 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 · 37 lines · 0 tokens per session scan A b79ddce78de8

Subscribe to this mod's changes

integrity-checks-orchestrator is an agent published in the GitHub repository seanrreid/RAD_framework (5 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 620 tokens. 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

cpp-reviewer

Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.

affaan-m/ECC · 41 tokens

reviewer

Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…

genkovich/sdd · 81 tokens

atomic-auditor

Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…

damusix/atomic-claude · 169 tokens

bt6-pr-auditor

Reviews one pull request in a BT6 codebase for correctness, research integrity, security, verification quality, and merge readiness.

elder-plinius/T3MP3ST · 32 tokens

Reviewer

Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.

monkilabs/opencastle · 30 tokens

security-auditor

Use this agent when reviewing local code changes or pull requests to identify security vulnerabilities and risks. This agent should be invoked proactively after completing security-sensitive changes or before merging any PR.

NeoLabHQ/context-engineering-kit · 40 tokens