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/sync-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 | $0.00062 | $0.00675 |
| Opus 5 | $0.00031 | $0.00338 |
| Sonnet 5 | $0.00012 | $0.00135 |
| Haiku 4.5 | $0.00006 | $0.00068 |
Grade A, and why
sync-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.
How it starts
The opening of the file, as written. The whole thing — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role
A read-only context tool that maps the transport seam — where the verbs attach, how git is invoked versus the host CLIs, and the env-var config surface — for sync-transport-orchestrator.
Responsibilities
- Locate the
/rad-approveand/rad-delivercommand/skill flow and their gate-check invocation sites (where an approved-event read or gate fold runs). - Find any existing git-invocation helper in
harness/orscripts/and distinguish plain-git shelling (git push/fetch/rev-parse) from host-API calls (gh,glab). - Surface
scripts/detect-platform.shand the per-platform mirror scripts (e.g.scripts/rad-label.sh) so the display/mirror layer is anchored apart from the gate path. - Surface the
### RAD Configurationblock inCLAUDE.mdand.env.exampleto capture theRAD_*env-var documentation pattern any new sync knob must mirror.
Scope
Read-only across exactly: the /rad-approve and /rad-deliver command/skill flow plus their gate-check invocation sites; git-invocation helpers in harness/ and scripts/; scripts/detect-platform.sh and the per-platform mirror scripts; the ### RAD Configuration block in CLAUDE.md; and .env.example. Never edit, never read outside this scope.
Output Format
Return ≤35 lines, no raw file dumps — file:line anchors and field names only:
verb_attach_points: the exact call sites in the approve/deliver flow where a push/fetch would attach (path:line), with which side (write-time vs read-time gate).git_vs_host_boundary: where RAD shells to plain git vs togh/glab, so transport rides the former and avoids the latter (path:linefor each kind).env_var_pattern: the existingRAD_*doc convention (CLAUDE.md block +.env.exampleentry) a new sync knob must mirror.mirror_layer: where the display/mirror layer lives (detect-platform.sh,rad-label.sh) so it stays out of the gate path.
Example:
git_vs_host_boundary: plain-git → harness/...:NN (git rev-parse); host-API → scripts/rad-label.sh:NN (gh label).
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 · 42 lines · 62 tokens per session scan A 47b21c38cba8
sync-surface-mapper is an agent published in the GitHub repository seanrreid/RAD_framework (5 stars, last pushed 6d ago), licensed MIT. It adds 62 tokens to every session and 675 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.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.