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 insideout-ai/make-it-work --skill close-my-loopsgit clone --depth 1 https://github.com/insideout-ai/make-it-workWrote 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/insideout-ai/make-it-work/close-my-loops)<a href="https://agentmods.dev/skills/insideout-ai/make-it-work/close-my-loops"><img src="https://agentmods.dev/badge/skills/insideout-ai/make-it-work/close-my-loops.svg" alt="Measured on agentmods" 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 | $0.00223 | $0.04506 |
| Opus 5 | $0.00112 | $0.02253 |
| Sonnet 5 | $0.00045 | $0.00901 |
| Haiku 4.5 | $0.00022 | $0.00451 |
Grade A, and why
close-my-loops 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 today.
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 — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Close My Loops
This skill has four parts. They build on each other but are each independently useful — jump to whichever one matches what the user asked for.
- Build/refresh
brain.md— a profile of the user's working life, from their own email/Slack. - Set up a Cowork Project so that file gets read automatically every session, instead of only when someone remembers to mention it.
- Set up a scheduled task that refreshes the file daily and sends a summary of what needs attention.
- On-demand 1:1 prep checklists — when the user asks to be prepared for a weekly/1:1 with a specific person, research that person's open threads and write the result into a persistent Slack canvas section for them, not just into the chat reply.
The four connect: Part 2 is what makes Part 1's file actually useful without the user re-uploading it every time, Part 3 is what keeps it current without the user having to ask again, and Part 4 is what turns "prepare me for X" from a one-off chat answer into something that persists in the same place the user already keeps notes for that person. A brain.md nobody re-reads, or one that goes stale, is much less valuable than the sum of its parts — so if the user only asks for Part 1, it's worth mentioning the other parts exist once the file is built.
Part 1: Build or refresh brain.md
What this produces
A single markdown file (default name brain.md) that a future Claude session can read to answer things like "find my important emails," "draft a reply to X in my style," or "who owns this initiative." It's not a knowledge base of facts about the world — it's a profile of the user's working life: who they talk to, how, and what's currently in flight.
The file has different kinds of content, and it matters that you keep them distinct:
- Stable content — role, reporting line, key people, communication style. Changes slowly; the most reusable part.
- Time-sensitive content — active initiatives, open loops awaiting a response. Goes stale within days. Always label it as a dated snapshot, not settled fact.
- A changelog — see below. This is what makes Parts 2 and 3 work over time.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- today Changed · +47 lines · +30 tokens per session 770a37744911
- 7d ago First seen · 121 lines · 193 tokens per session scan A 69236de80531
close-my-loops is a skill published in the GitHub repository insideout-ai/make-it-work (11 stars, last pushed yesterday), licensed MIT. It adds 223 tokens to every session and 4,506 once invoked, about $0.0011 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 2026-08-30.
Other skills, from other repositories
context-efficient-coding
Use ContextFlux to minimize coding-agent context and tool calls when exploring, planning, debugging, reviewing, or modifying an unfamiliar or multi-file repository. Trigger for codebase discovery, symbol search, architecture questions, cross-file changes, error tracing, review feedback, test discovery, or any request…
session-management
Context preservation, tiered summarization, resumability.
learn
Diagnose and fix agent behavioral surfaces when the user corrects a mistake — connects to Claude native memory.
keep-the-why
Extract and preserve the reasoning code cannot explain - decisions, rejected alternatives, workarounds, incidents, constraints - plus project setup and maintainer interviews. Not for what changed (see Keep a Changelog) - only why.
requirement-ledger
Guide Codex in turning a user-selected conversation, Agent Skill, Git project, or recent-work window into a context-aware personal improvement plan. When the host exposes bounded task history, retrieve related authorised context; otherwise request a bounded selection or export. Use for one-time audit, daily…
handoff
End-of-session save and next-session resume. Triggers "ending session", "wrapping up", "context window", "running out of context", "done for today" (save mode); "continue where we left off", "pick up where", "last session", "previous work", "resume" (resume mode).