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 instructions/agentevalhq/agenteval/tracinggit clone --depth 1 https://github.com/AgentEvalHQ/AgentEvalWhat 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 | $0.00999 | $0.00999 |
| Opus 5 | $0.00500 | $0.00500 |
| Sonnet 5 | $0.00200 | $0.00200 |
| Haiku 4.5 | $0.00100 | $0.00100 |
Grade A, and why
AgentEval tracing.instructions.md 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 yesterday.
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 — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tracing Implementation Guidelines
Core Tracing Components
Recording Agents
TraceRecordingAgent- Wraps agent to capture executionsChatTraceRecorder- Records multi-turn conversationsWorkflowTraceRecorder- Records multi-agent workflow steps
Replay Agents
TraceReplayingAgent- Replays recorded traces deterministicallyWorkflowTraceReplayingAgent- Replays workflow traces
Serialization
TraceSerializer- Save/loadAgentTraceto/from JSONWorkflowTraceSerializer- Save/loadWorkflowTraceto/from JSON
AgentTrace Structure
public class AgentTrace
{
public string Version { get; set; }
public string TraceName { get; set; }
public DateTimeOffset CapturedAt { get; set; }
public string? AgentName { get; set; }
public string? ModelId { get; set; }
public List<TraceEntry> Entries { get; set; }
public TracePerformance? Performance { get; set; }
public Dictionary<string, object>? Metadata { get; set; }
}
public class TraceEntry
{
public TraceEntryType Type { get; set; }
public int Index { get; set; }
public string? Prompt { get; set; }
public string? Text { get; set; }
public long? DurationMs { get; set; }
public TraceTokenUsage? TokenUsage { get; set; }
public List<TraceToolCall>? ToolCalls { get; set; }
public TraceError? Error { get; set; }
public bool IsStreaming { get; set; }
public List<TraceStreamChunk>? StreamingChunks { get; set; }
}
Recording Pattern
// Wrap real agent
await using var recorder = new TraceRecordingAgent(realAgent, "weather_test");
// Execute (calls real agent, captures result)
var response = await recorder.InvokeAsync("query");
// Get trace for storage
var trace = recorder.Trace;
// Save to file
await TraceSerializer.SaveToFileAsync(trace, "trace.json");
Replay Pattern
// Load saved trace
var trace = await TraceSerializer.LoadFromFileAsync("trace.json");
// Create replayer
var replayer = new TraceReplayingAgent(trace);
// Replay entries in order
while (!replayer.IsComplete)
{
var response = await replayer.InvokeAsync("prompt");
// Response is identical to original
}
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.
- yesterday First seen · 170 lines · 999 tokens per session scan A 4ce918262e69
AgentEval tracing.instructions.md is an instructions file published in the GitHub repository AgentEvalHQ/AgentEval (138 stars, last pushed yesterday), licensed MIT. It adds 999 tokens to every session, about $0.0050 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 2026-08-30.
Other instructions, from other repositories
zeroclaw CLAUDE.md
Instructions for zeroclaw-labs/zeroclaw, covering claude.md — zeroclaw (claude code), claude code settings, hooks and slash commands.
openagent CLAUDE.md
Claude Code instructions for the-open-agent/openagent, covering claude.md, commands, architecture, backend (go / beego) and frontend (react).
Tracely-ai CLAUDE.md
Claude Code instructions for Jwuthri/Tracely-ai, covering claude.md, commands, architecture, hard rules and gotchas.
nuwax AGENTS.md
Instructions for nuwax-ai/nuwax, covering ai agent system documentation, 系统概述, ai agent 架构, 核心组件 and ai 功能特性.
zhin zhin-plugin.instructions.md
Instructions for zhinjs/zhin, covering zhin plugin runtime authoring, package contract, convention directories, imports and native typescript and command routes.
OpenPersona AGENTS.md
Instructions for acnlabs/OpenPersona, covering agents.md, project overview, setup, project structure and architecture rules.