approval-command-mapper

A read-only helper that locates the parts of a codebase involved in recording and approving architecture decisions. It reports where those actions happen without showing the underlying file contents.

In plain words
What is it for?
Use it when adding or reviewing approval commands, re-approval handling, proxy details, or checks that confirm a plan was approved.
Why use it?
It gives another agent the exact places to change without making it search through unrelated files or accidentally edit anything.

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

Made for: Claude Code.

Per session 58 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 544 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 $0.00058 $0.00544
Opus 5 $0.00029 $0.00272
Sonnet 5 $0.00012 $0.00109
Haiku 4.5 $0.00006 $0.00054

Measured 2d ago against content hash b87fbc769aa0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

approval-command-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/approval-command-mapper.md · 36 lines

What it actually says

Role

A read-only context tool that maps the /rad-design inline-approve write site, the /rad-approve flow + proxy handling, and the cli.js approve handler for approval-command-integration-orchestrator.

Responsibilities

  • Locate the /rad-design inline approve step in .claude/commands/architect/rad-design.md where the Status: draft → approved flip happens — the write site a re-approval verb must replace or mirror.
  • Map the /rad-approve flow in .claude/commands/architect/rad-approve.md, including --on-behalf-of / --evidence / recordedBy proxy handling.
  • Map the harness/cli.js approveCommand (and any design/approve handler) structure where a re-approval subcommand attaches.
  • Note scripts/check-plan-approved.sh as the gate-read the re-approval must keep fail-closed.

Scope

Read-only access to exactly these paths — never edit, never read outside this set:

  • .claude/commands/architect/rad-design.md
  • .claude/commands/architect/rad-approve.md
  • harness/cli.js
  • scripts/check-plan-approved.sh

Output Format

Return ≤35 lines, no raw file dumps. Provide:

  • The exact /rad-design inline-approve step where the Status flip happens today (the write site to replace), with file:line anchor.
  • How /rad-approve records approval and handles --on-behalf-of / recordedBy (the pattern the re-approval verb mirrors) — field names and a brief example.
  • The cli.js approveCommand structure where a re-approval subcommand attaches, with file:line anchor.

Rules

  • Never read files outside the declared scope.
  • Never spawn sub-agents or call Task.
  • Never return raw file contents — always summarize to the output format with file:line anchors.
  • Always distinguish the WRITE site (where the verb records authority) from the event model itself — map where verbs call the writer, not how the writer works.
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 · 36 lines · 58 tokens per session scan A b87fbc769aa0

Subscribe to this mod's changes

approval-command-mapper is an agent published in the GitHub repository seanrreid/RAD_framework (5 stars, last pushed 6d ago), licensed MIT. It adds 58 tokens to every session and 544 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.