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 calsora/power-platform-github-copilot-kit --skill retrogit clone --depth 1 https://github.com/calsora/power-platform-github-copilot-kitWrote 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/calsora/power-platform-github-copilot-kit/retro)<a href="https://agentmods.dev/skills/calsora/power-platform-github-copilot-kit/retro"><img src="https://agentmods.dev/badge/skills/calsora/power-platform-github-copilot-kit/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/calsora/power-platform-github-copilot-kit/retro"><img src="https://agentmods.dev/badge/skills/calsora/power-platform-github-copilot-kit/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 | $0.00034 | $0.01001 |
| Opus 5.5 | $0.00014 | $0.00400 |
| Sonnet 5.5 | $0.00007 | $0.00200 |
| Haiku 4.5 | $0.00003 | $0.00100 |
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 6d 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Retrospective Skill
Context
This skill reviews previous coding sessions in a repository and helps identify practical improvements for future work. It is designed for Power Platform projects, but it stays focused on the coding session, repo structure, tooling, and working patterns rather than project delivery or business outcomes.
The goal is to keep the retrospective simple, evidence-based, and directly useful for improving how the repo and coding agent are used next time.
Example Trigger Phrases
- "Review the last coding session and tell me what went wrong."
- "Run a retrospective on this repo and suggest improvements for future coding work."
- "What should we improve in our Power Platform repo after this session?"
- "Summarise the issues from this coding session and identify better repo patterns."
What to Review
Look for problems and opportunities in these areas:
- repo navigation and discoverability
- unclear file ownership or responsibilities
- missing or weak guidance in AGENTS.md, CLAUDE.md, or docs
- poor code organization or scattered logic
- repeated mistakes that could be caught by linting, tests, or checks
- inefficient tool use or wasted exploration steps
- token consumption and context efficiency
- missing automation, validation, or guardrails
- unclear patterns for Power Platform implementation, naming, or structure
- documentation gaps that made future work harder
Simple Retrospective Format
Present the review in this order:
- What worked well
- What was difficult
- Root causes
- Recommended improvements
- Actions for the next coding session
Improvement Categories
- Navigation: the agent or developer struggled to find the right file, pattern, or dependency.
- Repo structure: files were hard to locate, duplicated, or disconnected from the rest of the solution.
- Guardrails: missing checks, tests, linting, validation, or repo guidance that could have caught problems earlier.
- Coding standards: repeated issues caused by lack of clarity in conventions, patterns, or review expectations.
- Tool economy: unnecessary exploration, duplicated searches, or inefficient workflows.
- Token usage: unnecessary context loading, repeated file reads, oversized outputs, avoidable tool calls, or delegation that did not save effort.
- Documentation: unclear instructions, missing context, or unsupported assumptions in the repo.
- Power Platform patterns: repeated issues with app structure, flow logic, Dataverse design, or solution organization.
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.
- 6d ago First seen · 91 lines · 34 tokens per session scan A 4f79c6ff7576
retro is a skill published in the GitHub repository calsora/power-platform-github-copilot-kit (6 stars, last pushed 7d ago), licensed MIT. It adds 34 tokens to every session and 1,001 once invoked, about $0.0001 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 2026-10-11.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
agentmail
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.
rowboat-spaces
How to work as a member of Rowboat Spaces, the team chat where people and agents work together. Load it once per session, before acting on any request that reaches you from Rowboat; it covers your setup, mentions and hand-offs, the tools, and files.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
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…