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-ticketsgit 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-tickets)<a href="https://agentmods.dev/skills/turvodnik/pf-workflow/pf-tickets"><img src="https://agentmods.dev/badge/skills/turvodnik/pf-workflow/pf-tickets/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/skills/turvodnik/pf-workflow/pf-tickets"><img src="https://agentmods.dev/badge/skills/turvodnik/pf-workflow/pf-tickets.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 | $0.00072 | $0.00550 |
| Opus 5 | $0.00036 | $0.00275 |
| Sonnet 5 | $0.00014 | $0.00110 |
| Haiku 4.5 | $0.00007 | $0.00055 |
Grade A, and why
pf-tickets 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 9d 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 — 27 lines — stays where its author put it; the contents beside it link to each section on GitHub.
pf-tickets — from spec to task packets
Always communicate with the user in the user's language (Russian in the origin system); packets follow the template.
Goal: turn the approved SPEC.md into packets, each executable in a separate fresh session with no access to this chat. Fresh session = small context = cheaper on limits and more precise in quality.
Slicing rules
- A packet is self-contained: the executor will see ONLY the packet + the project's AGENTS.md. Everything needed is inside: file paths, decisions from the spec, constraints.
- No placeholders: no "fill this in" or "roughly like this". Concrete files, concrete commands, concrete criteria.
- Size: one packet ≤ ~2 hours of one session's work. Comes out bigger — slice smaller.
- Dependencies — via
depends_on; mark independent work as parallelizable. - Every packet gets an executor recommendation: owner (claude|codex|gemini|vladimir) and model class (thinking/design — a senior model; mechanics against a ready plan — Sonnet-class).
- Packet acceptance criteria — verifiable by command or observation; derive them from the spec's criteria.
- Parallelism gateway (idea after workflow-planner): if ≥5 tickets are mutually independent (no
depends_onamong them) — offer the human a parallel launch instead of a queue: several fresh windows at once (works for any agent) or a subagent swarm in Claude Code. Name the price honestly: parallel — faster in wall time but more expensive in tokens (every executor carries its own context); a queue — cheaper but longer. The human decides.
Output
- Files
.agents/runtime/tasks/T-###-slug.mdperreferences/task-template.md(numbering continuous across the project). - In SPEC.md, the «Декомпозиция» section: the packet list in order.
- A digest for the human: a table (id, essence, depends on, executor), what can run in parallel, and the ready launch command for the first batch: new session → «выполни task-пакет T-00N по pf-do» — or with one command
/pf-auto: the whole pipeline by subagents to the end (the pf-auto skill).
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.
- 9d ago First seen · 27 lines · 72 tokens per session scan A 3faaa5337b3c
pf-tickets is a skill published in the GitHub repository turvodnik/pf-workflow (3 stars, last pushed 24d ago), licensed MIT. It adds 72 tokens to every session and 550 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
aip-tracker
Track Airflow Improvement Proposal (AIP) implementation progress by comparing Confluence specs against codebase evidence. Use when asked to assess, report on, or compare AIP status.
issue-triage
Triage Paperclip inbox issues that are stale, blocked, in-review, or assigned-but-not-progressing, and decide a single next action per issue (resume, reassign, unblock, escalate, or close).
multi-agent
A process for coordinating multiple coding agents by splitting work among scouts, workers, reviewers, and repair agents. Each agent has a defined role and task.
tencent-meeting-mcp
A Tencent Meeting assistant for scheduling meetings and working with participants, recordings, transcripts, and AI-generated meeting notes.
flow-next-plan
Plan a feature into a flow-next spec with tasks in .flow/. Use when asked to plan, spec out, or break down work (fn-N ids).
flow-next-tracker-sync
Project a flow-next spec to a tracker issue (Linear, GitHub, GitLab, Jira) and reconcile two-way. Use when asked to sync to a tracker. NOT plan-sync.