Borrowing it
Nothing to install: this file belongs to testdino-hq/testdino-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/testdino-hq/testdino-mcp/main/.claude/skills/retro/SKILL.mdgit clone --depth 1 https://github.com/testdino-hq/testdino-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/skills/testdino-hq/testdino-mcp/retro)<a href="https://agentmods.dev/skills/testdino-hq/testdino-mcp/retro"><img src="https://agentmods.dev/badge/skills/testdino-hq/testdino-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/skills/testdino-hq/testdino-mcp/retro"><img src="https://agentmods.dev/badge/skills/testdino-hq/testdino-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 | $0.00019 | $0.00725 |
| Opus 5 | $0.00010 | $0.00362 |
| Sonnet 5 | $0.00004 | $0.00145 |
| Haiku 4.5 | $0.00002 | $0.00072 |
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 11d 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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Run a retrospective on the work just completed.
When to Use
- After completing a non-trivial task (new tool, bug fix, refactor)
- After a task that required rework or user corrections
- After the self-correction protocol fired
- When the user explicitly asks
Workflow
1. Review What Happened
- Check
git difffor what changed - Scan conversation for user corrections, stops, or direction changes
- Count: how many times was the approach adjusted?
2. Categorize
| Outcome | Meaning |
|---|---|
| Clean | Worked first time, no rework |
| Corrected | User stepped in with a correction |
| Reworked | Had to redo — approach was wrong |
3. Write Lessons (for Corrected/Reworked only)
Write to auto-memory (feedback type) with:
- name: Short descriptive title
- description: One-line summary for future relevance matching
- Content:
- Trigger: What happened
- Wrong: What I did and why it was wrong
- Right: What should have been done instead
- Rule: The general principle (one sentence, reusable)
- Area: Which part of the project this applies to (tools, endpoints, docs, publishing, or "all")
4. Check for Promotions
Review existing auto-memory feedback entries. If the same lesson pattern appears 3+ times:
- Propose adding as a permanent rule to the Known Patterns & Pitfalls table in
CLAUDE.md - Get user approval before modifying CLAUDE.md
- Once promoted, note the promotion in the auto-memory entry
5. Check if Skills Need Updates
If a lesson reveals a gap in a skill workflow (e.g., /add-tool missed a step, /verify should check something extra):
- Identify which skill file needs updating
- Propose the specific change
- Get user approval before modifying
Output Format
## Retrospective
**Task:** [what was done]
**Outcome:** Clean / Corrected / Reworked
**Adjustments:** [N times the approach was changed]
### Lessons Learned
[If Corrected/Reworked — list each lesson with the rule]
### Promotions
[If any feedback pattern hit 3+ occurrences — propose CLAUDE.md update]
### Skill Updates
[If any skill workflow gap was identified — propose the fix]
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.
- 11d ago First seen · 94 lines · 19 tokens per session scan A 7768b4e5aadd
retro is a skill published in the GitHub repository testdino-hq/testdino-mcp (9 stars, last pushed 1mo ago), licensed MIT. It adds 19 tokens to every session and 725 once invoked, about $0.0001 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
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
shellm
Reference for the shellm system — recursive LLM shell, identity management, memory, skills, trajectory, and all CLI tools. Use when working on shellm itself, debugging agent behavior, or understanding how the pieces fit together.