What is tfw-identity?

An internal identity and profile-binding mechanism for separating a person, their roles, the task owner, and the AI's role.

Use it when an agent must validate identity bindings, handle profile collisions, or decide whether state may be saved locally.

It prevents uncertain or unsafe identity assignments from being guessed or written to persistent storage.

tfw-identity — Skill for Codex by saubakirov

Install

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.

Any agent

npx skills add saubakirov/trace-first-starter --skill tfw-identity

Clone the repo

git clone --depth 1 https://github.com/saubakirov/trace-first-starter

Made for: Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/saubakirov/trace-first-starter/tfw-identity/github.svg)](https://agentmods.dev/skills/saubakirov/trace-first-starter/tfw-identity)

Your own site

<a href="https://agentmods.dev/skills/saubakirov/trace-first-starter/tfw-identity"><img src="https://agentmods.dev/badge/skills/saubakirov/trace-first-starter/tfw-identity/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/saubakirov/trace-first-starter/tfw-identity"><img src="https://agentmods.dev/badge/skills/saubakirov/trace-first-starter/tfw-identity.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 76 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,926 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector warn 7 Sept 2026

SkillSpector: 3 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

medium analysis-evasion · line 1
Suspicious Unicode normalization or mixed-script content

Fix: Review the flagged content for security risks. Ensure no credentials, secrets, or sensitive data are exposed.
medium Rogue Agent · line 24
Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
medium Rogue Agent · line 24
Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.

How audits are shown

Origin original No closer match found in the catalogue.

Token cost

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	$0.00076	$0.02926
Opus 5	$0.00038	$0.01463
Sonnet 5	$0.00015	$0.00585
Haiku 4.5	$0.00008	$0.00293

Measured 6d ago against content hash 33969ed7638d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

tfw-identity 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 6d 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.

editions/02-assisted/.agents/skills/tfw-identity/SKILL.md · 100 lines

How it starts

The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.

TFW Identity

Сделай идентификацию незаметной частью сопровождения. Обычный человек отвечает своими словами; не показывай ему название skill, идентификатор профиля, YAML, project_id, путь хранилища, режимы реализации или служебные команды.

Это self-contained prompt-only процесс. Сам выбирай доступные средства текущей среды для чтения, проверки и безопасной записи; не требуй конкретную ОС, runtime, Python, Git, shell или исполняемый helper. Технические средства могут использоваться внутри работы ИИ, но не являются зависимостью конечного пользователя. Если обязательную safety-гарантию доказать нельзя, останови долговечную запись и используй только явно допустимый session-only fallback.

Разделяй пять полей

Текущий участник — человек в текущем человеческом чате; это заявленная атрибуция, не доказательство личности или полномочий.
Роль в компании и роль в проекте — разные поля профиля человека. Если они совпадают, один ответ можно записать в оба поля; не применимо допустимо.
Владелец задачи — неизменное поле существующего TRACE.md; новый чат и смена участника его не переписывают.
Роль ИИ — plan, handoff или review; она определяется этапом и точным именем Codex-задачи, а не профилем человека.

Startup state machine человеческого чата

Сначала определи тип чата. В автономной handoff/review-задаче пропусти human onboarding и local binding: текущий участник и обе его роли равны не применимо (автономная роль), владелец остаётся из согласованного trace, роль ИИ задаётся этапом.
В человеческом чате перечитай PROJECT.md. Допустимы ровно один маркер состояния и, для ИНИЦИАЛИЗИРОВАН, ровно один canonical UUID project_id; missing, duplicate или invalid state/ID — fail-closed.
Динамически прочитай team/*.md, кроме README.md. Каждый human-профиль должен иметь ровно по одному полю Идентификатор, Отображаемое имя, Тип: человек, Роль в компании, Роль в проекте; filename совпадает с identifier, а identifier соответствует ^[a-z0-9][a-z0-9_-]*$. Automation-профиль имеет Тип: automation, identifier automation:<slug>, filename automation-<slug>.md и обе role-строки; валидируй его, но исключай из human matching. Duplicate identifier, неоднозначное нормализованное отображаемое имя, missing/duplicate field или неверная schema блокируют выбор и запись. Уже валидные identifiers не пересчитывай.
Если проект НЕ ИНИЦИАЛИЗИРОВАН, не создавай local binding отдельно. Включи полное имя с явно подтверждённой фамилией, роль в компании и роль в проекте в первый из максимум трёх блоков обычной инициализации. После ответов создай surname-based профили по shared-write протоколу, сгенерируй новый стабильный project_id, заполни проект и попроси начать новую сессию из-за изменения AGENTS.md. Рабочую задачу не создавай.
Если проект инициализирован, проверь binding текущего project_id по разделу «Machine-local Assisted binding» независимо от числа профилей. Только полностью валидный fixed выбирает существующий human-профиль; ask, missing binding, отсутствие профилей или любая fail-closed ошибка приводят к одному вопросу. Единственный профиль без binding не выбирай молча: на новом или общем устройстве человек может быть новым участником.

Read the full file on GitHub · 100 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

agents/openai.yaml 547 B

Changes

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.

6d ago Changed · +64 lines · +39 tokens per session 33969ed7638d
10d ago First seen · 36 lines · 37 tokens per session scan A b40bc14f1daf

Subscribe to this mod's changes

tfw-identity is a skill published in the GitHub repository saubakirov/trace-first-starter (29 stars, last pushed today), licensed MIT. It adds 76 tokens to every session and 2,926 once invoked, about $0.0004 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.

agentic-ai ai knowledge-management product-engineering skills

create-custom-grader

Use when converting an existing benchmark, rubric, verifier, task YAML/JSON, or domain check into SkillEvaluator BYOG/BYOT custom evaluation.

NVIDIA/SkillEvaluator · 35 tokens

agent-ready-cloudflare

Audit and improve website readiness for AI agents using the Cloudflare "Is It Agent Ready?" scanner (isitagentready.com). Covers scanning via API, interpreting results, generating implementation prompts, and fixing every check. Use when the user mentions "agent ready", "isitagentready", "AI agent scan", "agent…

fabricioctelles/skills · 158 tokens

aidlc-master

Runs the AWS AI-DLC (AI-Driven Development Life Cycle) methodology end to end: an adaptive three-phase workflow (Inception → Construction → Operations) with human approval gates, a full audit trail, and all artifacts in aidlc-docs/. Use when the user says "Using AI-DLC", "AI-DLC", "AIDLC", "aidlc-master", or asks for…

fabricioctelles/skills · 243 tokens

slop-eval

Objectively evaluate a UI/web design against the pols.dev anti-slop design law: detect catalogued slop tells with cited evidence, score 8 weighted axes (color, type, components, layout, motion, execution, signature, cohesion), and emit a Slop Report with a 0–100 Slop Index and grade. Use when the user asks to…

fabricioctelles/skills · 142 tokens

security-specialist

Runs security audits on codebases — full scans, diff reviews, threat models, vulnerability triage, remediation guidance, and finding tracking. Activate when the user says "security scan", "audit this repo", "review this PR for security", "threat model", "triage vulnerabilities", "fix this vuln", or "track findings".

fabricioctelles/skills · 72 tokens

ralph-loop-kiro-specs

Automated iterative agent runner for spec-based development in Kiro. Wraps kiro-cli in a self-correcting bash loop that picks up tasks from a Kiro spec, implements them one at a time, verifies against exit criteria, and accumulates corrections and codebase patterns across iterations. Use this skill when the user…

fabricioctelles/skills · 192 tokens