plan-progress

plan-progress is a command for Claude Code from oborchers/fractional-cto. It costs 47 tokens per session (6,260 once invoked), scanned A, original, MIT.

A command that summarizes new work on the current Git branch and adds or updates the summary in a Markdown file, Linear ticket comment, or GitHub issue or pull-request comment. It can mark the work as shipped.

In plain words
What is it for?
Use it to record branch progress between work phases, include verification and out-of-scope notes, and publish a final shipped update.
Why use it?
It keeps progress updates in one place without rewriting earlier notes or duplicating them when run again. SHA-based tracking means it reports only commits not already covered.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: mentions subagents; names the AskUserQuestion tool.

Part of the planning-tools plugin — 5 skills, 7 commands, 3 agents shipped together

Good fit Use it to record branch progress between work phases, include verification and out-of-scope notes, and publish a final shipped update.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/oborchers/fractional-cto/plan-progress
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.

Clone the repo
git clone --depth 1 https://github.com/oborchers/fractional-cto

Made for: Claude Code.

Or install planning-tools, the plugin that ships this one along with the rest of its 5 skills, 7 commands, 3 agents.

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.

agentmods badge for plan-progress

README.md
[![agentmods](https://agentmods.dev/badge/commands/oborchers/fractional-cto/plan-progress/github.svg)](https://agentmods.dev/commands/oborchers/fractional-cto/plan-progress)
Your own site
<a href="https://agentmods.dev/commands/oborchers/fractional-cto/plan-progress"><img src="https://agentmods.dev/badge/commands/oborchers/fractional-cto/plan-progress/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.

agentmods 80×15 button for plan-progress

Your own site · 80×15
<a href="https://agentmods.dev/commands/oborchers/fractional-cto/plan-progress"><img src="https://agentmods.dev/badge/commands/oborchers/fractional-cto/plan-progress.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 47 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 6,260 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00047 $0.06260
Opus 5.5 $0.00019 $0.02504
Sonnet 5.5 $0.00009 $0.01252
Haiku 4.5 $0.00005 $0.00626

Measured 5d ago against content hash 39b00fd921a1, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

plan-progress 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 5d 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.

planning-tools/commands/plan-progress.md · 410 lines

How it starts

The opening of the file, as written. The whole thing — 410 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are synthesizing a progress entry for the current branch and writing it to the configured destination. The output style is codified by the planning-tools:progress-methodology skill — one dense paragraph per branch, evidence-rich, with inline sub-markers (Piggybacked:, Verification:, Out of scope:).

This command is safe to re-run — SHA-based idempotency means a second run between phases only narrates the new commits; the existing prose is preserved.

Input: $ARGUMENTS

Parse arguments:

  • --final → flip the entry to shipped state (prepend **Shipped <today> via PR #<N>.**, append ✅ to heading)
  • --destination <type>:<id> → one-off destination override. Examples: markdown:<path-to-progress-file> (any path; the plugin does not assume context/ or any other directory), linear:<ticket-id> (e.g., linear:AIA-1234), github:<owner>/<repo>#<number> (e.g., github:oborchers/fractional-cto#42). Does not persist to settings.
  • --style-from <path> → use the entries in this file as style exemplars instead of pulling from the destination
  • --ticket <id> → explicit source-ticket override (otherwise auto-detected from branch name)

Read the planning-tools:progress-methodology skill before Step 1 if you have not seen it this session — it owns the conventions every subsequent step depends on.


Step 1 — Detect git context

Run one bash block. Lift from /planning-tools:plan-tick Step 1:

git rev-parse --is-inside-work-tree || { echo "ERROR: not in a git repo"; exit 1; }
ROOT="$(git rev-parse --show-toplevel)"
BRANCH="$(git branch --show-current)"
[ -z "$BRANCH" ] && { echo "ERROR: detached HEAD — /planning-tools:plan-progress requires a named branch"; exit 1; }
BASE="$(git symbolic-ref --short refs/remotes/origin/HEAD 2>/dev/null | sed 's|^origin/||')"
[ -z "$BASE" ] && git rev-parse --verify --quiet origin/main >/dev/null && BASE=main
[ -z "$BASE" ] && git rev-parse --verify --quiet origin/master >/dev/null && BASE=master
[ -z "$BASE" ] && BASE=main
MERGE_BASE="$(git merge-base HEAD "$BASE" 2>/dev/null || git merge-base HEAD "origin/$BASE" 2>/dev/null)"
echo "ROOT=$ROOT"
echo "BRANCH=$BRANCH"
echo "BASE=$BASE"
echo "MERGE_BASE=$MERGE_BASE"

If not in a git repo or BRANCH is empty (detached HEAD), error with the message above and stop.

Compute the branch slug (used as the entry-key): strip leading feature/, fix/, chore/, bugfix/, hotfix/, or <user>/ prefixes; lowercase; replace _ and / with -. Save this as BRANCH_SLUG.


Read the full file on GitHub · 410 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.

  1. 5d ago First seen · 410 lines · 47 tokens per session scan A 39b00fd921a1

Subscribe to this mod's changes

plan-progress is a command published in the GitHub repository oborchers/fractional-cto (32 stars, last pushed 5d ago), licensed MIT. It adds 47 tokens to every session and 6,260 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 2026-10-13.