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 reeswrites/exo --skill trace-an-ideagit clone --depth 1 https://github.com/reeswrites/exoWrote 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/reeswrites/exo/trace-an-idea)<a href="https://agentmods.dev/skills/reeswrites/exo/trace-an-idea"><img src="https://agentmods.dev/badge/skills/reeswrites/exo/trace-an-idea/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/reeswrites/exo/trace-an-idea"><img src="https://agentmods.dev/badge/skills/reeswrites/exo/trace-an-idea.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 | $0.00102 | $0.01854 |
| Opus 5 | $0.00051 | $0.00927 |
| Sonnet 5 | $0.00020 | $0.00371 |
| Haiku 4.5 | $0.00010 | $0.00185 |
Grade A, and why
trace-an-idea 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 9d 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 — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Trace an idea
The owner's material is spread across surfaces that do not talk to each other: a published blog, private notes, half-finished drafts, saved links, long conversation threads. Exo is the one place they join. They cannot see across them. You can.
What they want is almost never a summary. It is the drift: where a position moved, where two dated pieces contradict each other, where a private note quietly reverses a published one. They already know the topic. The joins are the part they cannot get themselves.
Needs
| tool | without it |
|---|---|
whats_relevant |
the sweep loses its best opening move; start at notes_on and posts instead |
posts |
you can still trace the private side, but say that the published half is not in scope |
notes_on |
lean on whats_relevant, and say the map of what exists is missing |
drafts |
the note-to-post gap is invisible; do not claim a thing was never written |
saves |
you lose the borrowed-frame finding entirely; drop that section rather than guessing |
recent_topics, thread |
the freshest layer is gone; say the trace stops at the last written note |
open_threads |
report the unfinished questions you can see in drafts and stop there |
around_the_time |
only matters when they asked about a period rather than a topic |
An instance offers a subset of the surface and a held zone retires its tool (ADR-0020). Check what is actually listed before you plan the sweep, and say which surfaces you could not reach — an absent tool is not an empty record.
The sweep, in this order
Each step answers a different question, and the early ones tell you what to ask the later ones. Do not jump to the surface that looks most relevant.
| order | call | the question it answers |
|---|---|---|
| 1 | whats_relevant |
everything they have written that bears on this, by meaning. The best single first move |
| 2 | notes_on (titles first) |
what exists privately — a map, before you spend calls on bodies |
| 3 | notes_on / posts with full:true |
what they actually said, as opposed to what the title suggests |
| 4 | posts |
what got finished and published, with its live URL |
| 5 | drafts |
what stalled between the note and the post. stale_days finds what went cold |
| 6 | saves |
what they read. Input, never opinion |
| 7 | recent_topics, then thread |
what they argued out loud. Fresher than notes, which lag an act of capture |
| 8 | open_threads |
questions they asked themselves and never closed |
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.
- 9d ago First seen · 151 lines · 102 tokens per session scan A 7db672068e93
trace-an-idea is a skill published in the GitHub repository reeswrites/exo (0 stars, last pushed 4d ago), licensed MIT. It adds 102 tokens to every session and 1,854 once invoked, about $0.0005 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 2026-09-04.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…