Borrowing it
Nothing to install: this file belongs to nikolai-vysotskyi/trace-mcp. 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/nikolai-vysotskyi/trace-mcp/master/AGENTS.mdgit clone --depth 1 https://github.com/nikolai-vysotskyi/trace-mcpWrote 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/nikolai-vysotskyi/trace-mcp/agents-md)<a href="https://agentmods.dev/instructions/nikolai-vysotskyi/trace-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/nikolai-vysotskyi/trace-mcp/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/nikolai-vysotskyi/trace-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/nikolai-vysotskyi/trace-mcp/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 | $0.00464 | $0.00464 |
| Opus 5 | $0.00232 | $0.00232 |
| Sonnet 5 | $0.00093 | $0.00093 |
| Haiku 4.5 | $0.00046 | $0.00046 |
Grade A, and why
trace-mcp 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 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.
What it actually says
trace Tool Routing
IMPORTANT: For ANY code exploration task, ALWAYS use trace tools first. NEVER use host file-reading, grep, glob, or shell (ls, find) tools for navigating source code.
| Task | trace tool | Instead of |
|---|---|---|
| Find a function/class/method | search |
text grep |
| Understand a file before editing | get_outline |
full-file read |
| Read one symbol's source | get_symbol |
full-file read |
| What breaks if I change X | get_change_impact |
guessing |
| All usages of a symbol | find_usages |
text grep |
| All implementations of an interface | get_implementations |
directory search (ls/find) |
| All classes implementing X | search with implements filter |
text grep |
| Project health / coverage gaps | self_audit |
manual inspection |
| Dead code / dead exports | get_dead_code (mode: "exports_only") |
text grep for unused |
| Context for a task | get_feature_context |
reading 15 files |
| Tests for a symbol | get_tests_for |
glob + grep |
| Untested symbols (deep) | get_untested_symbols (deferred — load via load_tools) |
manual audit |
| HTTP request flow | get_request_flow (framework-gated) |
reading route files |
| DB model relationships | get_model_context (framework-gated) |
reading model + migrations |
| Component tree | get_component_tree (framework-gated) |
reading component files |
| Circular dependencies | get_circular_imports |
manual tracing |
| Task spanning many turns | trace_state_init once, then trace_state_patch / trace_state_add_dead_end per step, trace_state_get to re-read (deferred — load_tools({preset:"state"})) |
re-reading the whole transcript every turn |
Use host file-reading and grep tools ONLY for non-code files (.md, .json, .yaml, config) or before edit.
Start sessions with get_project_map (summary_only=true).
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 Changed · +1 lines · +63 tokens per session ba7aa030322c
- 6d ago Changed · -7 lines · -96 tokens per session 346466e7d450
- 10d ago First seen · 35 lines · 497 tokens per session scan A 77472c4bd895
trace-mcp AGENTS.md is an instructions file published in the GitHub repository nikolai-vysotskyi/trace-mcp (175 stars, last pushed today), licensed MIT. It adds 464 tokens to every session, about $0.0023 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
repobrain copilot-instructions.md
Copilot instructions for study8677/repobrain, covering github copilot bootstrap instructions and hard rule — query the repobrain hub first.
plugin-files-mode
Rosetta Plugin Mode Bootstrap.
weld copilot-instructions.md
Copilot instructions for configflux/weld: Use @docs/architecture/principles.md for architecture-sensitive changes.
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).