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.
npx agentmods add agents/seanrreid/rad_framework/approval-command-mappergit clone --depth 1 https://github.com/seanrreid/RAD_frameworkWhat 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.
| Model | Per session | Once 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 |
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.
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.mdwhere theStatus: draft → approvedflip 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/recordedByproxy handling. - Map the
harness/cli.jsapproveCommand(and any design/approve handler) structure where a re-approval subcommand attaches. - Note
scripts/check-plan-approved.shas 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.mdharness/cli.jsscripts/check-plan-approved.sh
Output Format
Return ≤35 lines, no raw file dumps. Provide:
- The exact /rad-design inline-approve step where the
Statusflip happens today (the write site to replace), withfile:lineanchor. - 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.jsapproveCommandstructure where a re-approval subcommand attaches, withfile:lineanchor.
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:lineanchors. - 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.
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.
- 2d ago First seen · 36 lines · 58 tokens per session scan A b87fbc769aa0
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.
Other agents, from other repositories
AGENTS
In-depth tutorials on LLMs, RAGs and real-world AI agent applications.
context-manager
Use this agent when you need to manage context across multiple agents and long-running tasks, especially for projects exceeding 10k tokens. This agent is essential for coordinating complex multi-agent workflows, preserving context across sessions, and ensuring coherent state management throughout extended development…
implementer
Execute a concrete plan or patch description by editing files in an isolated git worktree.
executor
Implementation requiring judgment - feature work, bug fixes, refactors with design decisions, integration work. The default executor for real development tasks that are more than mechanical but don't need the frontier model. Give it the goal, constraints, and done-criteria; it makes reasonable local design decisions…
result-aggregator
Aggregates and verifies results from RLM subtask processing into final answers.
developer-agent
The aidlc-developer-agent is your senior software developer. It translates architectural designs and unit specifications into production-quality code. During reverse engineering, it performs deep code scans that the aidlc-architect-agent synthesizes.