audit

A guide for reviewing Claude Code transcript files and identifying where token usage is concentrated. A transcript is the saved record of a coding-agent session.

In plain words
What is it for?
Use it to inspect input, output, cached text, model use, subagent activity, costly transcripts, and one safe next optimization experiment.
Why use it?
It provides evidence about usage hotspots before changes are made, while keeping local file names and commands private in its default report.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/ictechgy/context-guard/audit
Any agent
npx skills add ictechgy/context-guard --skill audit
Clone the repo
git clone --depth 1 https://github.com/ictechgy/context-guard

Made for: Claude Code, Codex.

Per session 29 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 416 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00029 $0.00416
Opus 5 $0.00015 $0.00208
Sonnet 5 $0.00006 $0.00083
Haiku 4.5 $0.00003 $0.00042

Measured 2d ago against content hash 28d596a38bfa, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

audit 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 2d 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.

plugins/context-guard/skills/audit/SKILL.md · 40 lines

What it actually says

ContextGuard Audit

Run a best-effort transcript audit, then interpret the result conservatively.

Default command:

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:

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;
  • model distribution;
  • query_source distribution: main, subagent, auxiliary;
  • top transcript files and commands observed;
  • generated recommendations with priority, reason, action, and evidence;
  • cache_friendliness status, bounded prefix/tail churn signals, and any cache-layout findings;
  • top likely causes and one safe next experiment.

Privacy: default output uses basename+hash transcript labels and command category+hash labels. Do not ask for --show-paths or --show-commands unless the user explicitly wants local identifiers in the report. Cache-friendliness diagnostics use bounded redacted segment hashes and do not print raw prompt text. Recommendations are heuristics; treat them as hypotheses, especially with small files or records counts.

Caveat: Claude Code transcript schemas can change. Treat this as an operational signal, not billing authority. cache_read/cache_creation and cache_friendliness are provider-cache diagnostics, not proof of ContextGuard-caused token reduction. For billing authority, use Claude Console, cloud-provider billing, or configured OpenTelemetry metrics.

Changes

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.

  1. 2d ago First seen · 40 lines · 29 tokens per session scan A 28d596a38bfa

Subscribe to this mod's changes

audit is a skill published in the GitHub repository ictechgy/context-guard (3 stars, last pushed 2d ago), licensed Apache-2.0. It adds 29 tokens to every session and 416 once invoked, about $0.0001 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 2026-08-31.

Related

Other skills, from other repositories