pf-spec

pf-spec is a skill for Claude Code, Codex from turvodnik/pf-workflow. It costs 86 tokens per session (651 once invoked), scanned A, original, MIT.

An interview-based specification skill for large tasks or new projects. It asks for the important decisions one at a time and records the answers in a SPEC.md file.

In plain words
What is it for?
Use it to define goals, exclusions, users, data, integrations, acceptance criteria, risks, and timing for a substantial project.
Why use it?
It helps uncover unclear scope, boundaries, risks, and acceptance conditions before implementation begins.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Codex.

Good fit Use it to define goals, exclusions, users, data, integrations, acceptance criteria, risks…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/turvodnik/pf-workflow/pf-spec
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 turvodnik/pf-workflow --skill pf-spec
Clone the repo
git clone --depth 1 https://github.com/turvodnik/pf-workflow

Made for: Claude Code, 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.

agentmods badge for pf-spec

README.md
[![agentmods](https://agentmods.dev/badge/skills/turvodnik/pf-workflow/pf-spec.svg)](https://agentmods.dev/skills/turvodnik/pf-workflow/pf-spec)
Your own site
<a href="https://agentmods.dev/skills/turvodnik/pf-workflow/pf-spec"><img src="https://agentmods.dev/badge/skills/turvodnik/pf-workflow/pf-spec.svg" alt="Measured on agentmods" height="20"></a>
Per session 86 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 651 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.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00086 $0.00651
Opus 5 $0.00043 $0.00326
Sonnet 5 $0.00017 $0.00130
Haiku 4.5 $0.00009 $0.00065

Measured 6d ago against content hash 5f99784391c5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

pf-spec 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.

skills/pf-spec/SKILL.md · 31 lines

How it starts

The opening of the file, as written. The whole thing — 31 lines — stays where its author put it; the contents beside it link to each section on GitHub.

pf-spec — interview down to a specification

Always communicate with the user in the user's language (Russian in the origin system); SPEC.md follows the template.

Goal: before work starts, learn everything the human decides and record it in SPEC.md. The human answers questions ONCE at the start — then the agents work autonomously.

Interview rules

  1. One question at a time. Wait for the answer. Do not dump a list of ten questions.
  2. Attach your recommended answer and its consequences to every question: "I would pick X because …; the cost is …" (in the origin system the answer is phrased in Russian). The human may simply agree.
  3. Facts learnable from files, code, git or the internet — find YOURSELF before asking. Ask only what is the human's decision: goals, boundaries, priorities, budgets, tastes.
  4. Topic order: goal and motivation → boundaries (what we do NOT do) → consumers of the result → data and sources → integrations and secrets (names only, per §5) → acceptance criteria → risks and reactions → timing/priority. 4a. Codex second opinion — ask once, here. Only when the spec involves code AND command -v codex succeeds (otherwise skip the question entirely — never advertise a tool the machine does not have). Ask: may executors run Codex as a read-only reviewer of their diffs in this project? Price: a few minutes and OpenAI quota per ticket; gain: an outside pass that does not inherit our blind spot. On «да» write .agents/codex-review.json{"enabled": true, "model": "gpt-5.6-luna", "effort": "max"} — and record the decision in the spec's assumptions. On «нет» write {"enabled": false} so nobody asks again. Details: pf-do/references/codex-review.md.
  5. Continue until every template section can be filled without invention. "I don't know" — offer a default and mark it in the spec as an assumption.
  6. Answer per §0: plain words + the term alongside.

Output

  1. Fill SPEC.md per references/spec-template.md in the project root (or the phase folder per project convention).
  2. Show the human a 10–15 line digest, ask for «ок» or corrections.
  3. After «ок» offer pf-tickets. A SPEC without the human's «ок» is a draft — no work happens on it.

Read the full file on GitHub · 31 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.

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.

  1. 6d ago First seen · 31 lines · 86 tokens per session scan A 5f99784391c5

Subscribe to this mod's changes

pf-spec is a skill published in the GitHub repository turvodnik/pf-workflow (3 stars, last pushed 22d ago), licensed MIT. It adds 86 tokens to every session and 651 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 2026-08-31.