audit SKILL.md skillB
audit from ictechgy/context-guard is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add ictechgy/context-guard/audit@git:20260906.ea89522Pins git:20260906.ea89522 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- B, 16 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- ictechgy/context-guard
- Path
plugins/context-guard/skills/audit/SKILL.md- Versions recorded
- 5
- Latest version
- git:20260906.ea89522, committed Sep 6, 2026
- First version recorded
- Jun 3, 2026
- Size
- 2,995 bytes
- Repository stars
- 3
- License
- Apache-2.0
Audit local Claude Code transcript usage and summarize likely token hotspots. Use when the user asks where Claude Code tokens are going or wants evidence before optimizing.
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
# ContextGuard Audit Run a best-effort transcript audit, then interpret the result conservatively. Default command: ```bash context-guard-audit ~/.claude/projects --top 20 --recommend ``` If the user supplies a path, audit that path instead. If no path is supplied, keep the default Claude projects path: ```bash if [ -n "$ARGUMENTS" ]; then context-guard-audit "$ARGUMENTS" --top 20 --recommend else context-guard-audit ~/.claude/projects --top 20 --recommend fi ``` Report: - observed token buckets: input, output, cache_read, cache_creation; - new tokens per turn (cache_creation distribution) and the "by preceding tool_result" table: this is the quantity billed under prompt caching. The table covers every counted turn, so read the `cold_start` / `cache_rewrite` / `incremental` fields beside it before naming a tool. Turns that wrote the cached prefix track context size at that moment rather than what a tool just returned, so trimming one result does not change them. When those turns dominate, say so instead of naming the table's top tool; - model distribution; - query_source distribution: main, subagent, auxiliary; - top transcript files and commands observed; …
Read the whole file at its exact version.
How to install
mdr add ictechgy/context-guard/audit@sha256:8635b1bf0339f0c1The line at the top of this page pins the label git:20260906.ea89522, 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_ehgni3oisbqhwzcq)
4 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between Jun 3, 2026 and Sep 6, 2026, about one every 24 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260906.ea89522 latest | 2026-09-06 | ea89522 | 2,995 B | B | view · diff |
| git:20260904.635a01b | 2026-09-04 | 635a01b | 2,681 B | B | view · diff |
| git:20260904.0ab517a | 2026-09-04 | 0ab517a | 2,633 B | B | view · diff |
| git:20260904.0c339ce | 2026-09-04 | 0c339ce | 2,317 B | B | view · diff |
| git:20260603.377f05a | 2026-06-03 | 377f05a | 1,944 B | B | view |
Audit of the latest version
- fail: Frontmatter declares a name
- pass: Frontmatter block present
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (2995 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
Starting a new one? Use a template for SKILL.md on mdpantry, which passes every one of these checks and says what to change in it.
Source
ictechgy/context-guard · 3 stars · license Apache-2.0 · pushed 2026-09-06 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_ehgni3oisbqhwzcq GET https://markdownregistry.com/api/v1/resolve?ref=ictechgy/context-guard/audit GET https://markdownregistry.com/api/v1/blob/8635b1bf0339f0c1b2380b9da1e4e0529a1d528740baa8b25fa0862664ad450b
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 ictechgy/context-guard
Every file in ictechgy/context-guard