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/event-fold-mappergit clone --depth 1 https://github.com/seanrreid/RAD_frameworkWrote 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.
[](https://agentmods.dev/agents/seanrreid/rad_framework/event-fold-mapper)<a href="https://agentmods.dev/agents/seanrreid/rad_framework/event-fold-mapper"><img src="https://agentmods.dev/badge/agents/seanrreid/rad_framework/event-fold-mapper.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00057 | $0.00608 |
| Opus 5 | $0.00028 | $0.00304 |
| Sonnet 5 | $0.00011 | $0.00122 |
| Haiku 4.5 | $0.00006 | $0.00061 |
Grade A, and why
event-fold-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 4d 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 — 40 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 gate event-fold, the events writer/provenance freezing, the event schema, and the branch-tip read sites for event-fold-orchestrator.
Responsibilities
- Locate
evaluateGateinharness/gates.jsand describe how it folds the event stream into a verdict — note that it is a pure fold with no special-case branches. - Find the writer in
harness/events.jsandrecordApproval, describing how write-time provenance (role,recordedBy) is frozen into the event at append time. - Surface the event schema and
gates.yaml— field names, required keys, and how a gate name maps to the events that satisfy it. - Locate the branch-tip read sites that the gate-check consumes (
rad gate <feature>andscripts/check-plan-approved.sh) where a fetch-and-compare divergence check could attach. - Report everything as file:line anchors plus terse event-shape notes — never raw file contents.
Scope
Read-only access to exactly: harness/gates.js (the evaluateGate fold), harness/events.js (the writer + recordApproval provenance freezing), the event schema / gates.yaml, and the branch-tip read sites (rad gate <feature>, scripts/check-plan-approved.sh). Never edit. Never read outside this scope.
Output Format
Return, in ≤35 lines, no raw file dumps:
- The current event shape with field names, e.g.
{ type, feature, role, recordedBy, ts }, and theevaluateGatefold location (file:line) and how it reduces events to a verdict. - How the writer freezes provenance (
role/recordedBy) at append time (file:line), so new ownership events can follow the same pattern. - Where the branch tip is read (file:line for
rad gate <feature>andscripts/check-plan-approved.sh) so a fetch-and-compare divergence check can attach. - The load-bearing invariant: the fold has no special-case branches — call out exactly where it stays branchless. Give concrete field names and one brief example event.
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 note where the fold stays branchless so new events extend the pattern rather than special-casing it.
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.
- 4d ago First seen · 40 lines · 57 tokens per session scan A 6ac162bfb890
event-fold-mapper is an agent published in the GitHub repository seanrreid/RAD_framework (5 stars, last pushed 9d ago), licensed MIT. It adds 57 tokens to every session and 608 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.