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.
npx skills add rubenzarroca/sdd-plugin --skill sdd-retrogit clone --depth 1 https://github.com/rubenzarroca/sdd-pluginWrote 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/skills/rubenzarroca/sdd-plugin/sdd-retro)<a href="https://agentmods.dev/skills/rubenzarroca/sdd-plugin/sdd-retro"><img src="https://agentmods.dev/badge/skills/rubenzarroca/sdd-plugin/sdd-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 | $0.00065 | $0.01950 |
| Opus 5 | $0.00032 | $0.00975 |
| Sonnet 5 | $0.00013 | $0.00390 |
| Haiku 4.5 | $0.00006 | $0.00195 |
Grade A, and why
sdd-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 8d 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 — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/sdd:retro — Post-feature retrospective
You are running a quick, conversational debrief after a feature is completed. This is entirely opt-in — the user chose to be here. Keep it light, useful, and short. No academic tone, no grading. Think of it as a 2-minute coffee chat about what just happened.
Step 1: Identify feature
Parse the feature name from $ARGUMENTS. If no argument is provided, read .sdd/state.json and look for features in completed state. If there is exactly one completed feature, use it. If there are multiple, list them and ask the user which one to reflect on.
If no features are in completed state, say: "No completed features found. Retro works best after finishing a feature — come back after /sdd:validate marks one as completed." Then stop.
Step 2: Read state
Read .sdd/state.json. Extract for the selected feature:
- Transitions array: the full sequence of state changes with timestamps and commands.
- Coaching profile: the current
coaching_profileobject (global, not per-feature). - Completed features count:
completed_featuresvalue.
Do NOT read specs, plans, tasks, or source code. Only state.json.
Step 3: Analyze the journey
From the transitions, determine:
- Duration: time from the first transition (
drafting → specified) to the last (validating → completed). - Path taken: did the feature go straight through, or were there backward transitions (e.g.,
implementing → tasked,specified → drafting)? Backward transitions are learning moments, not failures. - Number of tasks: count task entries in the feature's
tasksobject.
From the coaching profile, identify:
- Categories where
scaffoldedincreased during this feature's lifecycle: these are areas where Claude had to help. - Categories where
unscaffoldedincreased: these are areas where the user showed independent competence. - Strongest category: highest
unscaffoldedrelative toscaffolded. - Growth area: highest
scaffoldedrelative tounscaffolded.
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.
- 8d ago First seen · 168 lines · 65 tokens per session scan A 7ab161c5576e
sdd-retro is a skill published in the GitHub repository rubenzarroca/sdd-plugin (6 stars, last pushed 6mo ago), licensed MIT. It adds 65 tokens to every session and 1,950 once invoked, about $0.0003 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 skills, from other repositories
crap-analyzer
Use to produce a risk-based refactor + test plan for recently-changed code on a diff/branch/PR by computing CRAP (complexity × untested) on changed methods. Multi-language — TypeScript, JavaScript, Python, Java, Kotlin, Go, Ruby, C#, Rust, PHP — auto-discovers how the repo generates coverage. Triggers …
challenge
Adversarial review — Fable 5 stress-tests reasoning, Gemini checks knowledge. Use before plan or architecture decisions.
review
Business review — weekly health check, monthly close, or ad-hoc audit. Subcommands: weekly, monthly, check. Use for periodic reviews or metrics assessment.
nextjs-patterns
Next.js App Router — Server Components, Actions, streaming, caching. Use when building or migrating Next.js apps.
ship
Ship a build — pre-flight checks, deploy, document, verify, monitor. Use when deploying code, publishing packages, or releasing.
sitrep
Situational awareness — where am I, what was I doing, what's next. Context recovery after compression, confusion, or mid-session reorientation.