sdlc-retro

sdlc-retro is a command for coding agents from MCKRUZ/claude-code-sdlc. It costs 0 tokens per session (1,428 once invoked), scanned A, original, MIT.

A retrospective report that examines three accumulated project review records and looks for recurring patterns. A retrospective is a review of past work used to decide what should improve next.

In plain words
What is it for?
Use it to find issues that recur across review rounds, see which documents repeatedly become stale, measure how change candidates are handled, and summarize outstanding decisions. It reports findings but does not block work or edit files.
Why use it?
Individual reviews show isolated issues, while repeated issues may reveal a process problem. This report combines the history to show recurring findings, repeatedly outdated documents, refresh outcomes, and unresolved follow-up work.

Command

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the claude-code-sdlc plugin — 9 skills, 28 commands, 20 agents shipped together

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.

agentmods
npx agentmods add commands/mckruz/claude-code-sdlc/sdlc-retro
Clone the repo
git clone --depth 1 https://github.com/MCKRUZ/claude-code-sdlc

Or install claude-code-sdlc, the plugin that ships this one along with the rest of its 9 skills, 28 commands, 20 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 sdlc-retro

README.md
[![agentmods](https://agentmods.dev/badge/commands/mckruz/claude-code-sdlc/sdlc-retro.svg)](https://agentmods.dev/commands/mckruz/claude-code-sdlc/sdlc-retro)
Your own site
<a href="https://agentmods.dev/commands/mckruz/claude-code-sdlc/sdlc-retro"><img src="https://agentmods.dev/badge/commands/mckruz/claude-code-sdlc/sdlc-retro.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,428 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.01428
Opus 5 $0.00000 $0.00714
Sonnet 5 $0.00000 $0.00286
Haiku 4.5 $0.00000 $0.00143

Measured 4d ago against content hash a7b9810b6907, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sdlc-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 4d 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/sdlc-retro.md · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/sdlc-retro — Cross-Ledger Retro Roll-up

Read across the three advisory ledgers at once and surface what keeps happening — the retro question the per-round commands can't answer on their own. It reports four patterns:

  1. Recurring findings — a (category, target) group seen in >= 2 distinct review rounds is a candidate for a permanent check (this is how "findings become new checks").
  2. Repeat-stale artifacts — per downstream artifact, how many times it was dispositioned for staleness, and whether it is stale right now.
  3. Refresh funnel — per merged spec and by upstream stem: candidates → drifted → refreshed → rejected → still open. This doubles as the tuning signal for the divergence heuristic.
  4. Disposition debt rollup — combined honest-counting debt across all three ledgers, each line naming its source.

This is a sibling to /sdlc-audit-artifacts (freshness now) and /sdlc-audit (gate effectiveness). This command reads the accumulated history and reports the recurring shape of it. It reads three ledgers, computes nothing about people, and never blocks.

Instructions

  1. Resolve mode and repo root:

    • Workflow mode (default): look for .sdlc/state.yaml. Pass --state .sdlc/state.yaml. If not found, tell the user to run /sdlc-setup first.
    • Standalone mode (--repo <path>, or no .sdlc/ found): run against any repo with a .sdlc/ directory. The roll-up is only as deep as the ledgers in that repo — with a thin or missing ledger, each section degrades to "no data" (never a fabricated zero), and the missing context is noted by that "no data" line rather than guessed at.
  2. Run the roll-up (read-only — writes nothing, ever):

    uv run --project ${CLAUDE_PLUGIN_ROOT}/scripts ${CLAUDE_PLUGIN_ROOT}/scripts/retro_report.py --state .sdlc/state.yaml
    

    In standalone mode point it at any repo instead:

    uv run --project ${CLAUDE_PLUGIN_ROOT}/scripts ${CLAUDE_PLUGIN_ROOT}/scripts/retro_report.py --repo /path/to/repo
    

Read the full file on GitHub · 94 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. 4d ago First seen · 94 lines · 0 tokens per session scan A a7b9810b6907

Subscribe to this mod's changes

sdlc-retro is a command published in the GitHub repository MCKRUZ/claude-code-sdlc (4 stars, last pushed 6d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,428 tokens. 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.