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-replangit 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-replan)<a href="https://agentmods.dev/skills/turvodnik/pf-workflow/pf-replan"><img src="https://agentmods.dev/badge/skills/turvodnik/pf-workflow/pf-replan/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-replan"><img src="https://agentmods.dev/badge/skills/turvodnik/pf-workflow/pf-replan.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 | $0.00103 | $0.00668 |
| Opus 5 | $0.00051 | $0.00334 |
| Sonnet 5 | $0.00021 | $0.00134 |
| Haiku 4.5 | $0.00010 | $0.00067 |
Grade A, and why
pf-replan 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 — 30 lines — stays where its author put it; the contents beside it link to each section on GitHub.
pf-replan — changing course without losing finished work
Always communicate with the user in the user's language (Russian in the origin system). SPEC, ticket and journal formats stay as specified.
Mid-execution a new idea appeared or a decision changed. Two forbidden reflexes: continuing by inertia ("pity to waste the work") and redoing everything from scratch. The right path — assess the impact and edit surgically.
Steps
- Mini-interview (1–3 questions by pf-spec rules): what exactly changes and why; is it a new requirement on top, or a cancellation of an already-made decision?
- Impact tracing — along the chain «spec → tickets → commits»: find the SPEC sections the change touches → the tickets referencing them (
spec:in the frontmatter) → their dependents (depends_on). That is the revision zone; everything outside it stays untouched. - Classify and show the human a report (change nothing until «ок»):
- A — additive: does not touch finished work → append to SPEC + new tickets at the tail. No rollback.
- B — changes unfinished work: done tickets stay valid → rewrite or cancel the unfinished ones (
status: cancelled, reason in «Результат»), fix the SPEC. - C — invalidates finished work: some done tickets contradict the new decision → two options, each priced: (1) revert their commits (
git revert, list — from the tickets' «Результат») + new tickets; (2) rework tickets on top, no revert. Show both, recommend the cheaper.
- After «ок»: edit the SPEC (+ a record in «История изменений»: date, what, why, class A/B/C), mark cancelled tickets, create new ones (by pf-tickets rules), for class C — revert commits strictly by the list. If a HANDOFF is kept (pf-handoff companion) — update it: the cancelled goes to «Не делать» (§13).
- Journal (§10): what changed, the class, what was cancelled/reverted. This is the defense against "why is everything different from the spec?" a month later.
Why the rollback is cheap
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 · 30 lines · 103 tokens per session scan A 890615ebb2b1
pf-replan is a skill published in the GitHub repository turvodnik/pf-workflow (3 stars, last pushed 24d ago), licensed MIT. It adds 103 tokens to every session and 668 once invoked, about $0.0005 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.