Borrowing it
Nothing to install: this file belongs to VelimirMueller/vlm-code-context-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/VelimirMueller/vlm-code-context-mcp/main/.claude/commands/retro.mdgit clone --depth 1 https://github.com/VelimirMueller/vlm-code-context-mcpWrote 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/velimirmueller/vlm-code-context-mcp/retro)<a href="https://agentmods.dev/commands/velimirmueller/vlm-code-context-mcp/retro"><img src="https://agentmods.dev/badge/commands/velimirmueller/vlm-code-context-mcp/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/commands/velimirmueller/vlm-code-context-mcp/retro"><img src="https://agentmods.dev/badge/commands/velimirmueller/vlm-code-context-mcp/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 | $0.00000 | $0.00786 |
| Opus 5.5 | $0.00000 | $0.00314 |
| Sonnet 5.5 | $0.00000 | $0.00157 |
| Haiku 4.5 | $0.00000 | $0.00079 |
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 1mo 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/retro — Retrospective & Cumulative Learnings
Run retrospective for the current sprint and surface patterns from all past sprints.
Step 0 — Load Context (2 calls)
get_resume_state() # identify current sprint
load_phase_context({ phase: "retro", sprint_id }) # all retro data in one call
This returns sprint state, burndown, mood, retro patterns (including the try_next lifecycle: open/adopted/dropped counts), and velocity comparison.
Use this data to inform specific, data-backed retro observations. For example:
- "Velocity dropped 20% — what caused it?"
- "Auth tickets were flagged as underestimated in Sprint 3 AND Sprint 5"
- "QA agent mood has been declining for 3 sprints"
Step 1 — Add findings for the current sprint
Ask the three reflections one at a time as free text (they are genuinely open-ended — no option chips): went_well, went_wrong, try_next. Where a finding echoes loaded data, quote the numbers.
For try_next, confirm the action_owner via AskUserQuestion (the 9 team roles, recommended owner first).
add_retro_finding({ sprint_id: <id>, category: "went_well", finding: "<specific, data-backed>", role: "developer" })
add_retro_finding({ sprint_id: <id>, category: "went_wrong", finding: "<specific, data-backed>", role: "qa" })
add_retro_finding({ sprint_id: <id>, category: "try_next", finding: "<experiment>", role: "developer", action_owner: "developer" })
Lifecycle note: every try_next enters the planning gate as open. It will demand a triage decision (adopt / drop / defer via triage_retro_finding) at the next sprint's planning — capture happens here, the decision happens there. Tell the user this so the experiment doesn't feel like it vanishes into a list.
Step 2 — Cumulative summary
The retro patterns are already loaded from Step 0. Review them to surface:
- Recurring problems (went_wrong appearing multiple sprints)
- Consistent wins to keep doing (went_well)
- try_next follow-through: triage rate, applied rate, and the oldest still-open item
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.
- 1mo ago First seen · 66 lines · 0 tokens per session scan A bc3c74648fe4
retro is a command published in the GitHub repository VelimirMueller/vlm-code-context-mcp (5 stars, last pushed 18d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 786 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.
Other commands, from other repositories
backlog-from-demo
Turn a recorded product demo into a prioritized backlog with timestamped evidence.
onplana-connect
Sign in to the Onplana MCP server, then verify it works.
staff-event
Build a complete event staffing plan (configured-market match, W-2 rates, tier-based lead time, compliance) and prepare a buyer-submitted quote form.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.