y-retro

y-retro is a command for Claude Code from yashs33244/the_y_coding_standard. It costs 139 tokens per session (1,677 once invoked), scanned A, original, MIT.

A retrospective command for the eighth step of a sprint review cycle. It looks back at recent development work, such as shipped, unfinished, blocked, or surprising tasks.

In plain words
What is it for?
Reviewing commits, plans, and findings for a chosen time period and writing the results to a progress/YYYY-MM-DD-retro.md file.
Why use it?
It turns recent repository activity into a dated record, making recurring delays and patterns easier to notice later.

Command for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the the-y-coding-standard plugin — 1 skill, 10 commands shipped together

Good fit Reviewing commits, plans, and findings for a chosen time period and writing the results to a progress/YYYY-MM-DD-retro.md file.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/yashs33244/the_y_coding_standard/y-retro
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/yashs33244/the_y_coding_standard

Made for: Claude Code.

Or install the-y-coding-standard, the plugin that ships this one along with the rest of its 1 skill, 10 commands.

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 y-retro

README.md
[![agentmods](https://agentmods.dev/badge/commands/yashs33244/the_y_coding_standard/y-retro.svg)](https://agentmods.dev/commands/yashs33244/the_y_coding_standard/y-retro)
Your own site
<a href="https://agentmods.dev/commands/yashs33244/the_y_coding_standard/y-retro"><img src="https://agentmods.dev/badge/commands/yashs33244/the_y_coding_standard/y-retro.svg" alt="Measured on agentmods" height="20"></a>
Per session 139 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,677 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 $0.00139 $0.01677
Opus 5 $0.00069 $0.00839
Sonnet 5 $0.00028 $0.00335
Haiku 4.5 $0.00014 $0.00168

Measured 7d ago against content hash eadf676b84fa, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

y-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 7d 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.

commands/y-retro.md · 197 lines

How it starts

The opening of the file, as written. The whole thing — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/y-retro

The "Reflect." step. Step 08 of the Sprint Loop. The other steps move forward. This one looks back. What did we ship, what is still in flight, what got stuck, what surprised us. The point is not a feel-good ritual. The point is to notice patterns of friction before they become permanent. Output is progress/YYYY-MM-DD-retro.md with concrete entries that future-you can grep through.

Pre-flight

  1. We are in a git repo. If not, abort.
  2. Today's date is known. Use it to name the retro file.
  3. progress/ exists. If not, create it.
  4. plans/ and findings/ exist. If not, log that as a finding (no Sprint Loop discipline this period).

Ask the user once: "Retro window: since last retro, last 7 days, last 14 days, or custom range?" Default to since last retro, fall back to 7 days if no prior retro file exists.

Workflow

1. Determine the period

Find the most recent prior retro file in progress/. Use its date as the start. If none, use 7 days ago.

Capture:

  • Start date.
  • End date (today).
  • Day count.

2. Pull commit history

Run git log --since=<start> --pretty=format:'%h %s' --no-merges.

Capture every commit. Group by:

  • Conventional commit type: feat, fix, refactor, chore, docs, test.
  • Day.

Count totals per type. Note the busiest day.

If you have multiple branches, also run git log --since=<start> --all --pretty=format:'%h %an %s' to see contributor breakdown.

3. Pull plans activity

List files in plans/ modified during the period. For each:

  • Read its status frontmatter.
  • Categorize: created this period, shipped this period, abandoned this period, still in flight.

A plan that went from non-existent to status: shipped in one period is a healthy sprint signal. A plan that has been in-progress for three retros is a problem.

4. Pull findings activity

List files in findings/ modified during the period:

  • Governance findings: count P0/P1/P2/P3 across all *-govern.md.
  • Review findings: count P0/P1/P2/P3 across all *-review.md.
  • QA findings: count PASS / FAIL / PASS WITH CONCERNS across all *-qa.md.

Read the full file on GitHub · 197 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. 7d ago First seen · 197 lines · 139 tokens per session scan A eadf676b84fa

Subscribe to this mod's changes

y-retro is a command published in the GitHub repository yashs33244/the_y_coding_standard (2 stars, last pushed 3mo ago), licensed MIT. It adds 139 tokens to every session and 1,677 once invoked, about $0.0007 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.