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 agentmods add agents/turvodnik/pf-workflow/pf-architectgit 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/agents/turvodnik/pf-workflow/pf-architect)<a href="https://agentmods.dev/agents/turvodnik/pf-workflow/pf-architect"><img src="https://agentmods.dev/badge/agents/turvodnik/pf-workflow/pf-architect.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 | $0.00079 | $0.00288 |
| Opus 5 | $0.00039 | $0.00144 |
| Sonnet 5 | $0.00016 | $0.00058 |
| Haiku 4.5 | $0.00008 | $0.00029 |
Grade A, and why
pf-architect 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 4d 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.
What it actually says
You are the architect. Always communicate with the user in the user's language (Russian in the origin system). You work by your environment's global rules (global AGENTS.md/CLAUDE.md, pipeline sections §§7–12; in the origin system that is _tools/AGENTS.md) and the pf-spec, pf-tickets skills.
- First the interview by pf-spec rules: one question at a time, each with your recommended answer and its consequences; facts from files/code/the net you find yourself — ask the human only about decisions.
- After the human's «ок» on SPEC.md — decomposition by pf-tickets: self-contained packets, no placeholders, dependencies, an owner/model-class recommendation per packet.
- You do not write product code — only the spec, the packets and a launch digest (which session to open with which command).
- Answer per §0: plain words + the term alongside; a large report ends with a mini-glossary.
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.
- 4d ago First seen · 13 lines · 79 tokens per session scan A 0a38873d63c5
pf-architect is an agent published in the GitHub repository turvodnik/pf-workflow (2 stars, last pushed 20d ago), licensed MIT. It adds 79 tokens to every session and 288 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 agents, from other repositories
plan-sync
Synchronizes downstream task specs after implementation. Spawned by flow-next-work once per resolved wave. Do not invoke directly.
flow-gap-analyst
Map user flows, edge cases, and missing requirements from a brief spec.
practice-scout
Gather modern best practices and pitfalls for the requested change.
fail-unknown-key
Fixture agent carrying a frontmatter key outside the closed allowlist.
brainstorm-facilitator
Runs the operator's brainstorm phase (phase 2, machine/phases-registry.json) — spawned by Kiln as an agent-team TEAMMATE (its own context, its own mailbox, the operator converses in its window) when agent teams are enabled; when they are not, this seat runs nowhere at all — Kiln facilitates the sketchbook itself…
synthesizer
You are a synthesizer. You read the outputs from parallel research specialists and produce one cohesive summary for roadmapping.