A session-status tool that summarizes work as completed, open, or blocked items, including pending decisions and running processes. Its compact option also saves this state and creates a prompt for resuming later.

It helps track plans, unanswered questions, background tasks, worktree locations, and the next step after compacting a session.

It makes it easier to see what remains in a long coding session and avoid losing context when the session is shortened or restarted.

prog — Skill for Claude Code by nicograef/handbook

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 nicograef/handbook --skill prog

Clone the repo

git clone --depth 1 https://github.com/nicograef/handbook

Made for: Claude Code.

Or install nico, the plugin that ships this one along with the rest of its 10 skills, 1 agent, 4 hooks.

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/nicograef/handbook/prog/github.svg)](https://agentmods.dev/skills/nicograef/handbook/prog)

Your own site

<a href="https://agentmods.dev/skills/nicograef/handbook/prog"><img src="https://agentmods.dev/badge/skills/nicograef/handbook/prog/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/nicograef/handbook/prog"><img src="https://agentmods.dev/badge/skills/nicograef/handbook/prog.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 842 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	$0.00059	$0.00842
Opus 5.5	$0.00024	$0.00337
Sonnet 5.5	$0.00012	$0.00168
Haiku 4.5	$0.00006	$0.00084

Measured 2d ago against content hash cea1b0a774d6, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

prog 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 2d 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.

plugin/skills/prog/SKILL.md · 44 lines

How it starts

The opening of the file, as written. The whole thing — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Prog

Arguments: $ARGUMENTS. Apply every finding without asking; questions wait for /nico:decide at the end.

Never delete uncommitted work, unpushed commits, stashes or a dirty worktree. Never force past a git refusal.
Skip branches and worktrees this session or a live peer holds; ~/.claude/agent-bus.sh peers lists peers.
Under ~/.claude, delete only memory files the review flagged. Harness state ages out by its own retention.
Deletion is hard. dry-run lists every deletion and applies none.
Without close, running jobs keep running.
An action the harness or a permission rule blocks goes to the user, never around it.

Scope is the current project and repo. all adds every project's memory and every repo under ~/r, one opus subagent per project with a repo.

Steps

Verify. Recall and earlier verdicts are claims, not evidence. Check every item at every level against git, PRs, jobs, agents and a fresh check run. A failed claim becomes the verified state.
Check all shells and workflows. What is slowing the session down? How can we make the release cut and everything else faster and leaner? Anything ready to be cleaned and pruned yet?
Critically verify the progress and state of all shells, monitors, agents and workflows. Is any idle, stuck or outdated and to be removed?
Rewrite every state file to the verified state: scratchpad, memory and MEMORY.md, plan, programme and PRD files, run state, lead notes. Open steps go to the plan file, durable facts to memory.
Prune by content, not age: memory, rules, other sessions' scratchpad leftovers, fully ticked plans, shipped PRDs. Also merged or squash-merged branches with their remotes and clean worktrees. A memory deletion removes its index line too.
Sweep stale worktree entries, dead remote-tracking refs, dead bus sessions (agent-bus.sh sweep) and this session's finished jobs.
With close: additionally, run the close sweep below.
With compact: additionally, write verified state, plan path, worktree paths and open tasks to the scratchpad. Say /compact is safe and give a short resume prompt.
Report corrections, item status with evidence, running jobs, prune results, blocked commands and the close verdict.
Invoke the decide skill on every question the work needs from the user.

Read the full file on GitHub · 44 lines

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.

2d ago Changed · +2 lines cea1b0a774d6
18d ago Changed · -59 lines d6853607b0c9
28d ago Changed · +77 lines · +7 tokens per session c1f62edbbc9a
1mo ago Changed · +4 lines · +52 tokens per session 3e4c6689ceb2
1mo ago Changed 4368a9b77ea4
1mo ago Changed de5dd0a85a44
1mo ago First seen · 20 lines · 0 tokens per session scan A f256e2148a76

Subscribe to this mod's changes

prog is a skill published in the GitHub repository nicograef/handbook (2 stars, last pushed 2d ago), licensed MIT. It adds 59 tokens to every session and 842 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-14.

Productivity

prog next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
prognicograef/handbook	Skill	2	2d ago	MIT	A	59	Claude Code
orbit-notionnexu-io/open-design	Skill	106k	yesterday	Apache-2.0	A	117	Claude Code, Codex
agentmailpaperclipai/paperclip	Skill	111k	yesterday	MIT	A	30	Claude Code, Codex
Cortexdanielmiessler/LifeOS	Skill	20k	yesterday	MIT	A	184	Claude Code
rowboat-spacesrowboatlabs/rowboat	Skill	18k	yesterday	Apache-2.0	A	60	Claude Code, Codex
feishuHmbown/CodeWhale	Skill	41k	6d ago	MIT	A	33	Claude Code, Codex
pinchtab-mcppinchtab/pinchtab	Skill	11k	10d ago	MIT	A	52	Claude Code, Codex