agent-activity-audit

agent-activity-audit is a skill for Claude Code, Codex from hyperb1iss/sibyl. It costs 71 tokens per session (2,924 once invoked), scanned A, original, Apache-2.0.

A method for reviewing recent Claude Code and Codex session transcripts to understand how a developer tool or agent skill is being used in practice.

In plain words
What is it for?
It helps produce evidence-based findings for improving a CLI, MCP server, library, or skill, including grouped findings and reproducible analysis records.
Why use it?
It reveals recurring failures, sources of friction, and successful patterns that ordinary code review or performance tests would miss.

Skill for Claude CodeCodex

Written for Claude Code and Codex: allowed-tools in frontmatter, but also reads ~/.codex or $CODEX_HOME. Also seen: reads .claude/ paths; mentions subagents; positional $N argument.

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/hyperb1iss/sibyl/agent-activity-audit
Any agent
npx skills add hyperb1iss/sibyl --skill agent-activity-audit
Clone the repo
git clone --depth 1 https://github.com/hyperb1iss/sibyl

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for agent-activity-audit

README.md
[![agentmods](https://agentmods.dev/badge/skills/hyperb1iss/sibyl/agent-activity-audit.svg)](https://agentmods.dev/skills/hyperb1iss/sibyl/agent-activity-audit)
Your own site
<a href="https://agentmods.dev/skills/hyperb1iss/sibyl/agent-activity-audit"><img src="https://agentmods.dev/badge/skills/hyperb1iss/sibyl/agent-activity-audit.svg" alt="Measured on agentmods" height="20"></a>
Per session 71 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,924 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 5.1 $0.00071 $0.02924
Opus 5 $0.00036 $0.01462
Sonnet 5 $0.00014 $0.00585
Haiku 4.5 $0.00007 $0.00292

Measured 6d ago against content hash 6800591a03db, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

agent-activity-audit scanned grade A with 1 finding 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 6d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/extract_episodes.py, scripts/scan.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.

Reads agent configuration directorieslowAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

find ~/.claude/projects -name '*.jsonl' -newermt "$CUTOFF" > triage/claude_files.txt

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

skills/agent-activity-audit/SKILL.md · 308 lines

How it starts

The opening of the file, as written. The whole thing — 308 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Activity Audit

This skill executes a structured pass over recent agent transcripts to learn what's working and what's hurting. The original audit (May 2026) examined ~30 days of Claude Code and Codex sessions to improve Sibyl itself — see EXAMPLES.md for the full reproducible run.

The output is a synthesis report grounded in real session evidence, plus per-group findings files you can act on directly.


When to use

  • You maintain a system that agents call (CLI, MCP server, library, skill) and want signal beyond "did it work?"
  • You suspect agents are stumbling on something but can't name what.
  • A planning cycle is about to start and you want product priorities grounded in usage data, not vibes.
  • A new release shipped and you want to see how it landed in the wild.

Not for: general code review, security audits, performance benchmarking. This skill reads session transcripts; it doesn't analyze code.


Agent rules (READ FIRST)

  1. Always write artifacts under contexts/<analysis-name>-<date>/. Keep raw scans, episode extracts, and findings in one tree so the analysis is reproducible and the user can replay or extend it.

  2. Filter early, filter hard. Most transcripts are noise. Triage with cheap grep before spinning up parallel subagents — the goal is to give each subagent ~50-100 KB of focused episode data, not raw multi-MB JSONLs.

  3. Partition by date for the swarm. Date-based partitions are mutually exclusive, cover the full window, and make convergence across groups easy to spot (same theme in 4+ date ranges = durable issue).

  4. Each subagent writes findings to a file. Don't let agents return giant prose back to the main thread. Their job: produce findings/group_<X>.md, return a ≤250-word summary.

  5. Convergence-first synthesis. A pain point in 4+ groups is durable. Single-group findings warrant a sanity check before they're elevated. Count evidence; don't trust impressions.

  6. Verify before recommending fixes. Inspect current source for the surfaces the audit implicates. A finding like "the CLI rejects --kind gotcha" should point at the enum's actual location.

Read the full file on GitHub · 308 lines

Files

What ships with it

3 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. 6d ago First seen · 308 lines · 71 tokens per session scan A 6800591a03db

Subscribe to this mod's changes

agent-activity-audit is a skill published in the GitHub repository hyperb1iss/sibyl (57 stars, last pushed today), licensed Apache-2.0. It adds 71 tokens to every session and 2,924 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

ori-memory

Persistent agent memory with learning retrieval. Knowledge graph on markdown files — capture insights, decisions, research, and learnings during work, then retrieve them weeks or months later. Use when knowledge is too valuable to lose but too much to inject into every prompt.

aayoawoyemi/Ori-Mnemos · 54 tokens

forgetful-entities

Model the things knowledge attaches to — people, organisations, devices, products, system components. Use when a new thing surfaces that memories will reference, when relationships between things need recording (owns, depends on, part of), or when another skill routes a pointable thing here. Litmus: an entity is a…

ScottRBK/forgetful · 80 tokens

forgetful-explore

Explore the Forgetful knowledge graph when flat search isn't enough — cross-project investigations, "what do we know about X", entity-centred questions, tracing how decisions connect. Use when recall returns fragments that reference entities or trail across domains. Walks memories, entities, and relationships into one…

ScottRBK/forgetful · 65 tokens

remnic-memory-workflow

Shared memory workflow for Claude Code agents connected to Remnic — recall before acting, observe during work, remember at the end. Trigger phrases include "what do you remember about", "save this for later", "any context from last time".

joshuaswarren/remnic · 54 tokens

remnic-remember

Store a durable memory in Remnic so every connected agent can recall it. Trigger phrases include "remember this", "save this for later", "add a note that".

joshuaswarren/remnic · 39 tokens

remnic-entities

Browse entities in the Remnic knowledge graph and surface their facts and relationships. Trigger phrases include "tell me about the entity", "look up", "what do we know about".

joshuaswarren/remnic · 41 tokens