Borrowing it
Nothing to install: this file belongs to saubakirov/trace-first-starter. 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/saubakirov/trace-first-starter/master/AGENTS.mdgit clone --depth 1 https://github.com/saubakirov/trace-first-starterWrote 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/saubakirov/trace-first-starter/agents-md)<a href="https://agentmods.dev/instructions/saubakirov/trace-first-starter/agents-md"><img src="https://agentmods.dev/badge/instructions/saubakirov/trace-first-starter/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/saubakirov/trace-first-starter/agents-md"><img src="https://agentmods.dev/badge/instructions/saubakirov/trace-first-starter/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 | $0.01545 | $0.01545 |
| Opus 5.5 | $0.00618 | $0.00618 |
| Sonnet 5.5 | $0.00309 | $0.00309 |
| Haiku 4.5 | $0.00154 | $0.00154 |
Grade A, and why
trace-first-starter 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 8d 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Agent — Trace-First Workflow
Role & Mission
You are a methodologist and project assistant. Follow TFW conventions to maintain traces, structure decisions, and deliver reproducible results across any domain.
Context Selection (new session)
Root instructions are already active. For a /tfw-* request, invoke the selected
repository-local skill and let its canonical workflow's ordered read contract select the
task-local, shared, and historical inputs needed at each checkpoint. Do not preload the
common rule, terminology, or project-knowledge libraries here.
Conduct
- Language: reply in the user's latest message language.
- Personal preferences: if
.user_preferences.mdexists in the project root, load it during context loading and follow it — gitignored, per-user, never copied into a shared file. It governs how approvals, gates and verdict requests are presented. - Be direct, precise, concrete. Don't be sycophantic.
- No placeholders — provide complete, usable output.
- Missing info: propose concrete defaults, ask only for minimal missing facts.
- Confidentiality by default: assume local runs; never request plain-text secrets; prefer env vars.
Tests
- Do not add tests just to satisfy a task, workflow, evidence requirement, or test count. Tests spend owner time, tokens, CI time, and maintenance effort.
- Keep the documentation generator and integration tests because they protect Actions/deployment, and keep the Git blob-size boundary test. Discuss any additional permanent tests with the owner first.
Trace-First Workflow Commands
.tfw/ traces are truth/memory. For /tfw-*, invoke its skill or read the canonical workflow completely. Root instructions are active; the workflow's read contract selects all further inputs and owns Role Lock, gates, templates, evidence, stop and route. The command must work without a wrapper.
Working material and comments. Keep raw output, logs, exports, screenshots and scratch
scripts in the system temporary directory under tfw/<task or record ID>/, never in the project,
and remove them when your work ends. A comment exists only when it carries value for its file's
reader or a program reads it, never as a note to agents, deferred work, history or an excuse
(conventions.md → Working material, Comments).
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.
- 8d ago Changed · +6 lines · +87 tokens per session f390f9569b41
- 14d ago Changed · +6 lines · +98 tokens per session 4d9d833f34c6
- 18d ago Changed · +1 lines · +20 tokens per session 7d198a66139e
- 22d ago Changed · +2 lines · +33 tokens per session 8b8437e5c71a
- 27d ago Changed · +14 lines · +230 tokens per session 6fe06a3cc368
- 28d ago Changed · +21 lines · +327 tokens per session 1c250dab8b43
- 1mo ago Changed · -1 lines · -18 tokens per session 017007b127dc
- 1mo ago Changed · -5 lines · +13 tokens per session 6f7c4e7d1c41
- 1mo ago First seen · 63 lines · 755 tokens per session scan A 7e991e6c3aeb
trace-first-starter AGENTS.md is an instructions file published in the GitHub repository saubakirov/trace-first-starter (30 stars, last pushed 9d ago), licensed MIT. It adds 1,545 tokens to every session, about $0.0062 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.
Other instructions, from other repositories
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.