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.
npx skills add turvodnik/pf-workflow --skill pf-specgit clone --depth 1 https://github.com/turvodnik/pf-workflowWrote 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/skills/turvodnik/pf-workflow/pf-spec)<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>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 | $0.00086 | $0.00651 |
| Opus 5 | $0.00043 | $0.00326 |
| Sonnet 5 | $0.00017 | $0.00130 |
| Haiku 4.5 | $0.00009 | $0.00065 |
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.
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
- One question at a time. Wait for the answer. Do not dump a list of ten questions.
- 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.
- 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.
- 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 codexsucceeds (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. - 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.
- Answer per §0: plain words + the term alongside.
Output
- Fill
SPEC.mdperreferences/spec-template.mdin the project root (or the phase folder per project convention). - Show the human a 10–15 line digest, ask for «ок» or corrections.
- After «ок» offer
pf-tickets. A SPEC without the human's «ок» is a draft — no work happens on it.
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.
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 First seen · 31 lines · 86 tokens per session scan A 5f99784391c5
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.
Other skills, from other repositories
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
development
An index of programming guidance for Python, Go, Rust, TypeScript, Java, C++, and shell scripting.
tencent-docs
A Tencent Docs assistant for creating, reading, editing, organizing, importing, and exporting online documents, spreadsheets, presentations, diagrams, and forms.
post-build-flow
Handles workflow verification and setup after build-workflow succeeds, or when the message contains workflow-verification-follow-up or workflow-setup-required. Load after direct builds, when verificationReadiness requires action, or on orchestrator verify/setup follow-up turns.
wechat-article-pro
A WeChat public-account publishing assistant that searches for current topics, writes long-form articles, creates a cover image, and formats the result for publishing.
wechat-search
Search WeChat Official Account articles using OpenClaw's web search, Tavily API, and web fetch capabilities with compliance-focused design.