Borrowing it
Nothing to install: this file belongs to gokeshenzhen/TraceWeave. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/gokeshenzhen/TraceWeave/main/AGENTS.mdgit clone --depth 1 https://github.com/gokeshenzhen/TraceWeaveWrote 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/instructions/gokeshenzhen/traceweave/agents-md)<a href="https://agentmods.dev/instructions/gokeshenzhen/traceweave/agents-md"><img src="https://agentmods.dev/badge/instructions/gokeshenzhen/traceweave/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/gokeshenzhen/traceweave/agents-md"><img src="https://agentmods.dev/badge/instructions/gokeshenzhen/traceweave/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.08922 | $0.08922 |
| Opus 5.5 | $0.03569 | $0.03569 |
| Sonnet 5.5 | $0.01784 | $0.01784 |
| Haiku 4.5 | $0.00892 | $0.00892 |
Grade A, and why
TraceWeave AGENTS.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 1mo 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 — 245 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidance
Domain Context and Authorized Scope
TraceWeave is a local EDA/RTL simulation-debugging project for semiconductor designs and simulation artifacts that the user owns or is authorized to analyze.
VCD and FSDB are local digital simulation waveform databases.
In this repository, terms such as scan, sweep, handshake, protocol, interface, payload, trace, driver, load, and connectivity refer to digital-logic signals, bus behavior, waveform transitions, and elaborated-netlist relationships.
protected IP means semiconductor intellectual property. narrow_condition_injection is an RTL structural-analysis category for control-logic conditions.
Repository tasks are limited to local source code, local waveform and log files, test fixtures, and locally configured EDA tools. Do not access unrelated external systems or resources.
For performance optimizations:
-
Establish a measurable baseline before making substantial implementation changes when practical.
-
Prefer preserving public MCP tool interfaces and output schemas. Intentional interface or schema changes are allowed when explicitly requested or when they provide a justified architectural benefit; update callers, tests, documentation, and compatibility handling accordingly.
-
Preserve FSDB thread-safety and observable cancellation and timeout behavior. Changes to locking, scheduling, worker, or execution models are allowed when justified by evidence and covered by focused regression tests.
-
Add regression tests appropriate to the behavioral risk of the change, and use reproducible before/after benchmarks for performance-sensitive changes.
-
Report the tested workload, benchmark conditions, measured results, memory impact when relevant, and any behavioral or compatibility trade-offs before claiming a performance improvement.
Installation Discipline
When a user supplies this repository URL and explicitly asks to install TraceWeave, treat that as the repository-local full EDA profile unless the user explicitly requests the portable PyPI profile. First run the read-only check:
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.
- 1mo ago Changed · +3 lines · +47 tokens per session 14a40fb6bdbe
- 1mo ago Changed · +93 tokens per session 4550a43cd9d9
- 1mo ago Changed · +1 tokens per session 6a7d73fd51e7
- 1mo ago Changed · +14 lines · +436 tokens per session bb214ba5cc70
- 2mo ago First seen · 228 lines · 8,345 tokens per session scan A 9c5d47cd20d8
TraceWeave AGENTS.md is an instructions file published in the GitHub repository gokeshenzhen/TraceWeave (129 stars, last pushed 25d ago), licensed MIT. It adds 8,922 tokens to every session, about $0.0357 per session on Opus 5.5. 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.
TraceWeave AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| TraceWeave AGENTS.mdgokeshenzhen/TraceWeave | Instructions file | 129 | 25d ago | MIT | A | 8,922 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| vscode model-prompts.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 2,022 | GitHub Copilot |