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/audit-surface-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 | $0.00050 | $0.00703 |
| Opus 5 | $0.00025 | $0.00351 |
| Sonnet 5 | $0.00010 | $0.00141 |
| Haiku 4.5 | $0.00005 | $0.00070 |
Grade A, and why
audit-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.
How it starts
The opening of the file, as written. The whole thing — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role
Read-only context tool that maps the rad-insights aggregation, the kickoff session-start report, and the event-log read helpers for the audit-surface-orchestrator.
Responsibilities
- Locate where
/rad-insightssynthesizes and outputs the report (section pattern to extend with auto-clear counts/trends); file:line anchor - Locate where
kickoffreports active plan status at session start (the briefing section where auto-clear summary line attaches); file:line anchor - Identify the event-log read helper in
harness/events.jsthat countsapprovedevents and can be extended for policy provenance; function name + signature
Scope
Read scope: the rad-insights skill (.agents/findings.jsonl reader + report synthesis), the kickoff skill (session briefing), and the event-log read helpers in harness/events.js (the fold/read side only). Nothing outside this scope — read side only, never the event writer (recordApproval).
Output Format
Report in ≤35 lines, no raw file dumps. Structure:
- rad-insights extension point:
.claude/commands/shared/rad-insights.mdline (e.g., "Step 5, after the### Recommended Focus Areasblock") - kickoff briefing anchor:
.claude/skills/kickoff/SKILL.mdline (e.g., "Step 3, after the plan status grouping") - event-log read helper: function name + signature from
harness/events.js(e.g.,reduce(history)returns{ approvals }array where each carriesrole+recordedByprovenance)
Example output:
rad-insights: .claude/commands/shared/rad-insights.md line 165
Pattern: Insert "### Auto-Cleared Changes" section after "### Recommended Focus Areas"
Source: Extend the %cycle aggregation to count approved events where data.role === "policy"
kickoff: .claude/skills/kickoff/SKILL.md line 57
Pattern: After plan status groups, add "Auto-cleared: N changes since {date}"
Source: Call read helper to count approved events with policy provenance this session
event-read helper: harness/events.js line 129 function reduce(history)
Returns: { approvals: [{actor, ts, role?, recordedBy?}] } — iterate to count role='policy'
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.
- 3d ago First seen · 46 lines · 50 tokens per session scan A d73dc6dba131
audit-surface-mapper is an agent published in the GitHub repository seanrreid/RAD_framework (5 stars, last pushed 7d ago), licensed MIT. It adds 50 tokens to every session and 703 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
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.