r-context-audit SKILL.md skillA
r-context-audit from rfxn/rdf is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add rfxn/rdf/r-context-audit@git:20260902.42a192dPins git:20260902.42a192d in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- rfxn/rdf
- Path
adapters/claude-plugin/output/skills/r-context-audit/SKILL.md- Versions recorded
- 1
- Latest version
- git:20260902.42a192d, committed Sep 2, 2026
- Size
- 5,586 bytes
- Repository stars
- 20
- License
- GPL-2.0
Measure, score, and report on Claude Code context overhead for this.
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
# /rdf:r-context-audit — Context Weight Audit Measure, score, and report on Claude Code context overhead for this workspace. Identifies bloat, tracks drift from baseline, and produces actionable optimization recommendations. Run periodically (weekly, or after adding skills/memory/governance) to catch context creep before it impacts session quality. ## Arguments - `$ARGUMENTS` — optional: `--fix` to apply Tier 1 quick wins automatically ## Protocol ### 1. Run Measurement Script Execute the automated measurement script: ```bash bash ~/.rdf/state/context-audit.sh ``` If a baseline file exists at `~/.rdf/context-audit-baseline.json`, run with comparison mode: ```bash bash ~/.rdf/state/context-audit.sh --baseline ~/.rdf/context-audit-baseline.json ``` Parse the JSON output. Do NOT make additional file reads or greps — the script measures everything. Then measure RDF's own always-loaded boot cost: ```bash bash ~/.rdf/state/rdf-overhead.sh ``` Surface the three deploy figures from its JSON — `default_boot_tokens` (~0.1K, lessons index only), `rules_boot_tokens` (~2.1K, adds the unscoped core governance rule), and `lite_boot_tokens` (~0.7K, rdf-lite condensed …
Read the whole file at its exact version.
How to install
mdr add rfxn/rdf/r-context-audit@sha256:d75c8115f2d6bb37The line at the top of this page pins the label git:20260902.42a192d, 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_ev2klhafo4e46dav)
1 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 1 version of this file, committed on Sep 2, 2026.
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 (5586 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
rfxn/rdf · 20 stars · license GPL-2.0 · pushed 2026-10-28 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_ev2klhafo4e46dav GET https://markdownregistry.com/api/v1/resolve?ref=rfxn/rdf/r-context-audit GET https://markdownregistry.com/api/v1/blob/d75c8115f2d6bb37a8dbe90487e16417608a8ccd06b9d2eab5666990f42ff43a
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.