A workflow retrospective skill that reviews journals, task records, and Git activity across projects. It looks at how work progressed and where processes could improve.

Use it for periodic reviews of project workflows, automation maturity, unused skills or agents, and proposed process changes.

It helps reveal stalled work, repeated questions, missing records, and improvements that may reduce cost or risk.

pf-retro — Skill for Claude Code and Codex by turvodnik

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-retro

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/turvodnik/pf-workflow/pf-retro/github.svg)](https://agentmods.dev/skills/turvodnik/pf-workflow/pf-retro)

Your own site

<a href="https://agentmods.dev/skills/turvodnik/pf-workflow/pf-retro"><img src="https://agentmods.dev/badge/skills/turvodnik/pf-workflow/pf-retro/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/turvodnik/pf-workflow/pf-retro"><img src="https://agentmods.dev/badge/skills/turvodnik/pf-workflow/pf-retro.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 121 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 590 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.

Model	Per session	Once invoked
Fable 5.1	$0.00121	$0.00590
Opus 5	$0.00060	$0.00295
Sonnet 5	$0.00024	$0.00118
Haiku 4.5	$0.00012	$0.00059

Measured 8d ago against content hash 366a02a5d5c7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

pf-retro 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 8d 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-retro/SKILL.md · 35 lines

How it starts

The opening of the file, as written. The whole thing — 35 lines — stays where its author put it; the contents beside it link to each section on GitHub.

pf-retro — reviewing the workflows

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

Goal: regularly look at the facts (journals, packets, git) and propose improvements. The retro itself is level L1: report and proposals only, change nothing without the human's «ок».

Data collection (period — since the previous retro)

The paths below are the author's environment (~/ai — projects root, _tools/ — the utility folder, _tools/reports/ — retro reports); in your environment substitute your own projects root, reports folder and search method.

All projects' journals: ~/ai/*/.agents/journal/*.md for the period (quick slice — _tools/history-search.sh).
Task packets: blocked, plus those hanging in review/in_progress longer than a week.
Git: activity per project (git log --since=...), projects with no commits at all.
Usage: which skills/plugins/agents were actually applied (per journals), which — not once in 2 periods.

Analysis

What stalled: blocked packets, redone work, repeated questions to the human about the same thing.
Discipline: where the journal was not kept, where packets closed without «Результат» — holes in the history.
Automation candidates: anything repeated by hand ≥3 times over the period.
Automation maturity levels — per references/maturity-scale.md; promotion only after 2 clean runs, an incident = demotion.
Dead weight: skills/plugins/agents unused for 2 periods — detach candidates (less context — lower limit spend).
Context (if the pf-handoff companion is installed): review ~/.claude/context-state/compacts.log and the period's HANDOFF quality; adjust §13 thresholds by facts.

Output

Report _tools/reports/retro-YYYY-MM-DD.md per references/retro-template.md.
Proposals as a list, each with price, risk and "what happens if we don't" (§0).
Record the human's decisions in the report; accepted changes — as separate tasks.

Read the full file on GitHub · 35 lines

Files

What ships with it

2 files 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.

8d ago First seen · 35 lines · 121 tokens per session scan A 366a02a5d5c7

Subscribe to this mod's changes

pf-retro is a skill published in the GitHub repository turvodnik/pf-workflow (3 stars, last pushed 24d ago), licensed MIT. It adds 121 tokens to every session and 590 once invoked, about $0.0006 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.

Claude Code Planning Project management agent-skills ai-agents codex task-pipeline workflow

pf-retro

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

pf-retro — reviewing the workflows

Data collection (period — since the previous retro)

Analysis

Output

What ships with it

What this file has done since we first saw it

Other skills, from other repositories

aip-tracker

issue-triage

multi-agent

tencent-meeting-mcp

flow-next-plan

flow-next-tracker-sync