Home / garrytan / gbrain · plugin-variants/gbrain-coding/skills/context-audit/SKILL.md · GitHub

context-audit skillA

context-audit is agent-read markdown (skill) from garrytan/gbrain: Token-hygiene audit of the always-loaded context stack — CLAUDE.md, AGENTS.md, auto-memory MEMORY.md, and the bootstrap-rendered identity files (SOUL.md, USER.md, ACCESS_POLICY.md, HEARTBEAT.md) or their harness equivalents. Finds redundancy, contradictions, stale content, compression candidates, and skill-extraction candidates; produces a ranked action list sorted by token savings with a risk class per finding. REPORT-ONLY: this skill never edits any audited file. Recommendations for bootstrap-.

Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.

What the file says

# context-audit — Token Hygiene for the Always-Loaded Context Stack

> **Convention:** see [conventions/brain-first.md](../conventions/brain-first.md)
> — before running a fresh audit, check the brain for prior audit reports
> (`gbrain recall "context audit report"`) so you can compute token DRIFT since
> the last run and avoid re-flagging findings the user already declined.
>
> **Convention:** see [conventions/quality.md](../conventions/quality.md) —
> every finding cites its file and evidence; no unsourced claims.

## What this is

Every file that loads on every turn is a per-turn tax: tokens, latency, and —
past a point — instruction-following quality. Always-loaded files accrete
(append-only release notes, promoted memory blocks nobody re-reads, rules
restated in three files that drift into contradiction). This skill audits the
whole always-loaded stack at once and returns a ranked, evidence-cited action
list sorted by token savings.

It is an auditor, not a surgeon. It measures, finds, ranks, and recommends.
The user (or a skill the user explicitly invokes afterward) applies changes.

## Scope: what counts as "always-loaded"
…

Read the whole file at its exact version.

How to install

Latest version
mdr add garrytan/gbrain/context-audit@v1.0.0
Exact content
mdr add garrytan/gbrain/context-audit@sha256:450c7529b6d1eee7

Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_7gherciauq7iqfq3.svg)](https://markdownregistry.com/a/art_7gherciauq7iqfq3)

1 badge views in 30 days

Versions

versioncommittedcommitsizeaudit
v1.0.0 latest2026-09-15 f1fbdfb 12,198 BA view · diff
v1.0.02026-08-17 489e277 11,492 BA view

Audit of the latest version

A  17 of 17 checks passed. Deterministic, no model, same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (12198 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

GitHub

garrytan/gbrain · 30,275 stars · license MIT · pushed 2026-09-23 · branch master

API

GET https://markdownregistry.com/api/v1/artifacts/art_7gherciauq7iqfq3
GET https://markdownregistry.com/api/v1/resolve?ref=garrytan/gbrain/context-audit
GET https://markdownregistry.com/api/v1/blob/450c7529b6d1eee7fbd7c87b8d24e88b58c32a097e79ef7e598d4c94a98a5b5c

Your agent 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.

More from garrytan/gbrain

AGENTS.md agents
garrytan/gbrain · AGENTS.md
git:20260921.6ebc629 · audit B · 30,275 stars
CLAUDE.md claude
garrytan/gbrain · CLAUDE.md
git:20260921.6ebc629 · audit A · 30,275 stars
DESIGN.md design
garrytan/gbrain · DESIGN.md
git:20260519.3a0e111 · audit A · 30,275 stars
DESIGN.md@admin design
garrytan/gbrain · admin/DESIGN.md
git:20260503.f082501 · audit A · 30,275 stars
gbrain skill
garrytan/gbrain · docs/integrations/qm-harness-snippets/SKILL.md · Search and write the company knowledge brain. Use for any question about the org, people, projects, decisions, or…
git:20260801.aff34a4 · audit A · 30,275 stars
reference-pack skill
garrytan/gbrain · examples/skillpack-reference/skills/reference-pack/SKILL.md · Reference skill demonstrating the 10/10 skillpack contract. Adds a "what does this skillpack do" answer to the user's…
git:20260520.bc9f777 · audit A · 30,275 stars
llms-full.txt llmstxt
garrytan/gbrain · llms-full.txt
git:20260921.6ebc629 · audit F · 30,275 stars
llms.txt llmstxt
garrytan/gbrain · llms.txt
git:20260921.6ebc629 · audit A · 30,275 stars
brain-ingest-gate skill
garrytan/gbrain · plugin-variants/gbrain-coding/skills/brain-ingest-gate/SKILL.md · Pre-write quality gate for content entering the brain. No raw copies: a bare cp/mv into the brain repo is a bug. Before…
v1.0.0 · audit A · 30,275 stars
brain-link-discipline skill
garrytan/gbrain · plugin-variants/gbrain-coding/skills/brain-link-discipline/SKILL.md · When you report a brain page to the user — created, edited, committed, or relayed from a subagent — a working link is…
v1.0.0 · audit A · 30,275 stars
brain-ops skill
garrytan/gbrain · plugin-variants/gbrain-coding/skills/brain-ops/SKILL.md · Brain knowledge base operations. The core read/write cycle: brain-first lookup, read-enrich-write loop, source…
v1.2.0 · audit A · 30,275 stars
concept-synthesis skill
garrytan/gbrain · plugin-variants/gbrain-coding/skills/concept-synthesis/SKILL.md · Deduplicate and synthesize raw concept stubs into a tiered intellectual map (T1 Canon to T4 Riff), tracing idea…
v0.2.0 · audit A · 30,275 stars

Every file in garrytan/gbrain

Other files named context-audit

context-audit skill
jpeetz/agent-skills · skills/development/finding-unknowns/skills/context-audit/SKILL.md · Use when agent context is bloated or contradictory.
v1.0.0 · audit A · 9 stars
context-audit skill
greglas75/zuvo · skills/context-audit/SKILL.md · Context health monitoring. Analyzes include loading trends from context-metrics.log, audits CLAUDE.md/rules/settings…
git:20260802.56ae227 · audit A · 7 stars
context-audit skill
adamlinscott/claude-skills · skills/context-audit/SKILL.md · [Adam''s Skills] Audits a repository''s Claude context-injection setup — CLAUDE.md, CONTEXT.md, docs/, .claude/agents/…
git:20260911.623fe4a · audit A · 3 stars

Browse by kind, by grade A, or by owner.