system-audit

A system-audit skill reviews an AI agent setup, including its instructions, memory, tools, supporting agents, infrastructure, and claimed results. It requires each finding to be backed by evidence such as a file line, command output, or query result.

In plain words
What is it for?
Use it for quick, standard, or deep reviews of an agent system, followed by safe fixes and a ranked list of remaining work.
Why use it?
Agent systems can accumulate outdated rules, repeated facts, unused tools, and unsupported assumptions. The audit helps identify what works, what has drifted, what is missing, and what can be removed.

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/awrshift/agent-memory-kit/system-audit
Any agent
npx skills add awrshift/agent-memory-kit --skill system-audit
Clone the repo
git clone --depth 1 https://github.com/awrshift/agent-memory-kit

Made for: Claude Code, Codex.

Per session 225 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,617 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 100% copy Near-identical to another mod 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 $0.00225 $0.02617
Opus 5 $0.00112 $0.01308
Sonnet 5 $0.00045 $0.00523
Haiku 4.5 $0.00022 $0.00262

Measured yesterday against content hash 2978082a5e67, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

system-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 yesterday.

The scan reads SKILL.md. This mod also ships 3 executable files (scripts/collect.sh, scripts/usage_config.py, scripts/usage.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Origin

This is a copy

100% identical to system-audit — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

plugins/memory-kit/skills/system-audit/SKILL.md · 154 lines

How it starts

The opening of the file, as written. The whole thing — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.

System audit — «что работает / что дрейфует / чего нет / что удалить»

An agent system accretes. Good patterns and bad ones, dead rules nobody reads, facts restated in five places with three of them stale, tools that only ran once. This skill is the periodic sweep that keeps it evolving without inflating: it measures which layers actually fire, deletes what doesn't, and reports findings that carry evidence rather than impressions.

The one thing that makes this audit different from a checklist: every claim must be backed by something you touched with your own hands — a file:line, a command's output, a query result. An unverified observation is labelled гипотеза and never counted in the verdict.

Step 0 — Scope, depth, delta (2 minutes, always)

  1. Depth. Pick from what the user asked, default standard:
    • quick — deterministic collector + lenses 1, 4, 7 inline, no subagents. ~10 min. Use for a routine "как мы", or when the user asks mid-work.
    • standard — collector + all 7 lenses, lenses 2-6 fanned out to parallel recon subagents (model="sonnet"), synthesis + adjudication inline. The default.
    • deep — standard + an independent architecture critique (idea-validator, model="opus") and an external-family second opinion (/memory-kit:second-opinion), + a fresh-check of external facts (pricing, model ids, deprecated APIs) via WebSearch.
  2. Scope autodetect. Run the collector (step 1) — it reports which layers actually exist in this repo. A lens whose layer is absent is reported as н/п, never invented. Never audit node_modules/, .git/, build output, or vendored code.
  3. Delta. Read the newest prior report in context/audits/ (or wherever it lives). For each of its priorities: done · partially · ignored. An audit whose last round was ignored has one finding worth more than all the others — say so first.

Step 1 — The deterministic collector (before any reasoning)

# from the repo being audited; pass a path as $1 to audit a different repo
bash "${CLAUDE_PLUGIN_ROOT}/skills/system-audit/scripts/collect.sh" > /tmp/system-audit-facts.md

Read the full file on GitHub · 154 lines

Files

What ships with it

5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. yesterday First seen · 154 lines · 225 tokens per session scan A 2978082a5e67

Subscribe to this mod's changes

system-audit is a skill published in the GitHub repository awrshift/agent-memory-kit (31 stars, last pushed yesterday), licensed MIT. It adds 225 tokens to every session and 2,617 once invoked, about $0.0011 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to system-audit, differing in 0 lines, and is treated as a copy.

Related

Other skills, from other repositories

bridge-sync

End-of-sprint batch-sync: pushes ALL pending scope:core + scope:org commits from the local user branch to BOTH upstreams (open-bridge + your org overlay) in one operation, with per-destination scrubbing and parallel PR creation. Complements /promote (per-commit) and /contribute (per-file) with a sprint-level workflow.…

bks-lab/open-bridge · 118 tokens

briefing

Assembles a session context briefing from your configured issue tracker, recent git history, and active work signals. Use when: starting a new session, resuming after a break, user says 'catch me up', 'what was I working on', 'where did I leave off', context recovery after compaction, or user asks for project…

backchainai/backchain-plugins · 109 tokens

mcaf-agile-delivery

Shape delivery workflow around backlog quality, roles, ceremonies, and engineering feedback. Use when defining how the team plans, tracks work, and turns feedback into durable improvements.

managedcode/dotPilot · 40 tokens

kayba-stage-5-action-plan

Triage each insight into discard/code-fix/prompt-fix and produce a prioritized action plan with specific recommendations. Trigger when the user says "run stage 5", "make action plan", "triage skills", or when invoked by the kayba-pipeline orchestrator. Requires eval outputs from stages 1-4.

kayba-ai/agentic-context-engine · 74 tokens

kayba-stage-2-domain-context

Gather domain context about the repository and agent — system prompt, tool definitions, domain docs, and behavior patterns from traces. Trigger when the user says "run stage 2", "gather context", "domain context", or when invoked by the kayba-pipeline orchestrator.

kayba-ai/agentic-context-engine · 64 tokens

kayba-stage-1-api-analysis

Fetch pre-computed insights from the Kayba API and build a structured summary. Does NOT upload traces or trigger generation — analysis is assumed to already exist. Trigger when the user says "run stage 1", "get insights", "fetch skills", "kayba analyze", or when invoked by the kayba-pipeline orchestrator. Requires the…

kayba-ai/agentic-context-engine · 93 tokens