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 MotWakorb/ai-agent-dev-team --skill retrogit clone --depth 1 https://github.com/MotWakorb/ai-agent-dev-teamWrote 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/motwakorb/ai-agent-dev-team/retro)<a href="https://agentmods.dev/skills/motwakorb/ai-agent-dev-team/retro"><img src="https://agentmods.dev/badge/skills/motwakorb/ai-agent-dev-team/retro/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.
<a href="https://agentmods.dev/skills/motwakorb/ai-agent-dev-team/retro"><img src="https://agentmods.dev/badge/skills/motwakorb/ai-agent-dev-team/retro.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00039 | $0.02915 |
| Opus 5.5 | $0.00016 | $0.01166 |
| Sonnet 5.5 | $0.00008 | $0.00583 |
| Haiku 4.5 | $0.00004 | $0.00292 |
Grade A, and why
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 2mo 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 — 207 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Session Retrospective
Write a retrospective for the current session. Be honest — the PO can take meaningful feedback and expects it.
Model Selection
If you spawn agents to gather per-persona perspectives, pass model: sonnet. Tier modulation does not apply — retros are session-scoped, not component-scoped.
Process
- Review the full conversation to understand what happened this session
- Identify which personas were invoked or relevant (even if not explicitly called via
/skill) - Gather each persona's perspective on the session
- Write the retrospective file
- If relevant, update memory with durable lessons learned
- Run
/retro-syncto push the retro to the shared repo
Output Location
Write the retrospective to ~/retros/ named YYYY-MM-DD-HH_(three-word-topic).md.
Anonymization
Retros are synced to a public, multi-contributor GitHub repo (see retro-sync) so everyone using these skills can learn from them. Keep sensitive data out at generation time:
- Refer to the project by its pseudonym from
~/.claude/retro-project-map.txt(project-astyle) — in the filename's topic words and the body. If the project has no entry yet, assign the next unused pseudonym and append it to the map. Never use the real project, product, client, or employer name. Exception: the skill system itself (ai-agent-dev-team) — it's public and the corpus README links to it, so pseudonymizing it is theater - Never include credentials, tokens, API keys, or connection strings — not even expired or example ones from the session
- No customer/client names, emails, or any PII; refer to people by role ("the PO", "a user")
- No internal hostnames, IPs, or private URLs
- Don't paste verbatim file contents, command output, or data payloads — describe what happened, not the payload. Retros are about process
- Domain specifics that identify the project (unique feature names, table names, ticket prefixes) should be generalized when the lesson doesn't depend on them
- Before writing the file, reread the draft for those categories
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.
- 2mo ago First seen · 207 lines · 39 tokens per session scan A 4084fad08561
retro is a skill published in the GitHub repository MotWakorb/ai-agent-dev-team (2 stars, last pushed 2mo ago), licensed MIT. It adds 39 tokens to every session and 2,915 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 2026-08-31.
retro compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| retroMotWakorb/ai-agent-dev-team | Skill | 2 | 2mo ago | MIT | A | 39 | Claude Code |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | today | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | today | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 314k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |