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.
git clone --depth 1 https://github.com/yashs33244/the_y_coding_standardWrote 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/commands/yashs33244/the_y_coding_standard/y-retro)<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>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 | $0.00139 | $0.01677 |
| Opus 5 | $0.00069 | $0.00839 |
| Sonnet 5 | $0.00028 | $0.00335 |
| Haiku 4.5 | $0.00014 | $0.00168 |
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.
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
- We are in a git repo. If not, abort.
- Today's date is known. Use it to name the retro file.
progress/exists. If not, create it.plans/andfindings/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.
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.
- 7d ago First seen · 197 lines · 139 tokens per session scan A eadf676b84fa
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.
Other commands, from other repositories
template
Manage issue templates for streamlined issue creation.
sync-linear
Sync current work with Linear ticket status.
add-note
Add an internal or external note to a ConnectWise PSA ticket.
fest-show
Show festival progression (in-progress tasks, roadmap, and dependency view).
dispatcher
Pick the next-best repo to work on across the portfolio — rank free repos, recommend one, claim its lease atomically, and route to the entry command.
workpm
A project-management workflow for coordinating multiple AI workers through five stages. It includes task assignment, shared activity logs, worker replacement, and final checks.