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 mayank-io/mstack --skill summarize-this-sessiongit clone --depth 1 https://github.com/mayank-io/mstackWrote 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/mayank-io/mstack/summarize-this-session)<a href="https://agentmods.dev/skills/mayank-io/mstack/summarize-this-session"><img src="https://agentmods.dev/badge/skills/mayank-io/mstack/summarize-this-session/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/mayank-io/mstack/summarize-this-session"><img src="https://agentmods.dev/badge/skills/mayank-io/mstack/summarize-this-session.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 | $0.00055 | $0.00467 |
| Opus 5.5 | $0.00022 | $0.00187 |
| Sonnet 5.5 | $0.00011 | $0.00093 |
| Haiku 4.5 | $0.00006 | $0.00047 |
Grade A, and why
summarize-this-session 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.
What it actually says
Summarize Current Conversation
Review everything that has happened in this conversation and produce a two-section summary.
Instructions
Look back through the entire conversation history — every user message, every tool call, every result, every correction.
Produce the following two sections:
Ongoing Task
Summarize the work in progress:
- Initial Request: What the user originally asked for. State it clearly and concisely.
- Progress Made: What has been accomplished so far. List concrete deliverables (files created, bugs fixed, features implemented, decisions made). Be specific — reference file paths, function names, and outcomes.
- Next Steps: What remains to be done. If the task is complete, say so. If there are open questions or follow-ups, list them.
Continuous Improvement
Analyze the conversation for learning opportunities:
-
Mistakes Made by Claude: Actions Claude took that were wrong, suboptimal, or had to be redone. Include:
- What happened
- What the correct approach was
- Why Claude got it wrong (wrong assumption, missing context, tool misuse, etc.)
-
Mistakes Pointed Out by Human: Corrections the user explicitly made. Include:
- What the user corrected
- What Claude was doing wrong
- Whether this is a recurring pattern
-
Lessons Learned: Actionable takeaways from this conversation that would improve future sessions. These could be:
- Workflow improvements
- Tool usage patterns
- Project-specific conventions discovered
- Things that should be added to CLAUDE.md or memory
- Skills or plugins that would have helped
Formatting Rules
- Be honest and specific — don't gloss over mistakes or be vague
- If there were no mistakes in a category, say "None" — don't fabricate issues
- Keep each bullet concise but include enough detail to be actionable
- Reference specific messages or tool calls when describing mistakes
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 · 55 lines · 55 tokens per session scan A af49a5f7927d
summarize-this-session is a skill published in the GitHub repository mayank-io/mstack (6 stars, last pushed 3d ago), licensed MIT. It adds 55 tokens to every session and 467 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.
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.
Cortex
LifeOS memory, prior-session recall, and learning capture. USE WHEN capture this learning, document this learning, what did we learn recently, recent learnings, cortex, knowledge, knowledge base, search knowledge, what do we know about, archive, harvest, knowledge status, develop note, add to knowledge, add a people…
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.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
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.