context-audit SKILL.md skillA
context-audit from undefined-ui/second-brain-os is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add undefined-ui/second-brain-os/context-audit@git:20261007.c7fa35bPins git:20261007.c7fa35b in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- undefined-ui/second-brain-os
- Path
plugins/agents-course/skills/context-audit/SKILL.md- Versions recorded
- 2
- Latest version
- git:20261007.c7fa35b, committed Oct 7, 2026
- First version recorded
- Sep 29, 2026
- Size
- 3,221 bytes
- Repository stars
- 1,109
- License
- MIT
Audit an agent's context layout against the four places: system prompt, tools, history, tail. Use when the user asks to audit, review or fix their agent's context, prompt caching, token spend per turn, or CLAUDE.md / AGENTS.md layout. Read-only: reports findings and a fix list, changes nothing. Do NOT use for writing evals (evals-bootstrap) or for loop design (goal-test).
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Audit the context window Theory: [How models read context](https://secondbrainos.dev/#/read/course-1-context/how-models-read) and [The four places](https://secondbrainos.dev/#/read/course-1-context/the-four-places). Every piece of context belongs in exactly one of four places — a byte-stable system prompt, a frozen tool set, a compacting history, and a short live tail — and most agent problems trace back to something sitting in the wrong one. ## Core rule Report and rank; never edit. The output is an audit, and the user decides what to apply. If they ask you to apply fixes afterwards, that is a normal edit session, not this skill. ## Workflow 1. **Find the context sources.** Locate what actually reaches the model: system prompt (or CLAUDE.md / AGENTS.md for a Claude Code setup), tool definitions, and — if the project logs requests — one full mid-conversation payload. If nothing is logged, say so and audit the static files; ask for one captured request only if the user can produce it cheaply. 2. **Measure the five numbers.** Approximate token counts for: system prompt, tool definitions, message history, retrieved content, current query. …
Read the whole file at its exact version.
How to install
mdr add undefined-ui/second-brain-os/context-audit@sha256:252b98636d34a003The line at the top of this page pins the label git:20261007.c7fa35b, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_a7jocbwc56cpa7mx)
4 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, between Sep 29, 2026 and Oct 7, 2026, about one every 9 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261007.c7fa35b latest | 2026-10-07 | c7fa35b | 3,221 B | A | view · diff |
| git:20260929.fd3a523 | 2026-09-29 | fd3a523 | 3,251 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (3221 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
undefined-ui/second-brain-os · 1,109 stars · license MIT · pushed 2026-10-14 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_a7jocbwc56cpa7mx GET https://markdownregistry.com/api/v1/resolve?ref=undefined-ui/second-brain-os/context-audit GET https://markdownregistry.com/api/v1/blob/252b98636d34a003d39fe6c25112011e4c530fad8e9a4656907682a8c612bd03
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.
More from undefined-ui/second-brain-os
Every file in undefined-ui/second-brain-os