A skill your agent uses when analyzing WrongStack session journals to explain what happened in a session — tool usage and failures, token spend and cache efficiency, compactions, delegations, loops…
$ npx skills add WrongStack/WrongStack --skill audit-log -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install WrongStack/WrongStack audit-log --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/WrongStack/WrongStack.git skills-src && mkdir -p .claude/skills && cp -r skills-src/packages/core/skills/audit-log .claude/skills/audit-log && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "audit-log" agent skill from https://github.com/WrongStack/WrongStack/tree/main/packages/core/skills/audit-log into .claude/skills/audit-log/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "audit-log", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/WrongStack/WrongStack/tree/main/packages/core/skills/audit-logType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add WrongStack/WrongStack --skill audit-log -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install WrongStack/WrongStack audit-log --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/WrongStack/WrongStack.git skills-src && mkdir -p .agents/skills && cp -r skills-src/packages/core/skills/audit-log .agents/skills/audit-log && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "audit-log" agent skill from https://github.com/WrongStack/WrongStack/tree/main/packages/core/skills/audit-log into .agents/skills/audit-log/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "audit-log", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add WrongStack/WrongStack --skill audit-log -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install WrongStack/WrongStack audit-log --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/WrongStack/WrongStack.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/packages/core/skills/audit-log .cursor/skills/audit-log && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "audit-log" agent skill from https://github.com/WrongStack/WrongStack/tree/main/packages/core/skills/audit-log into .cursor/skills/audit-log/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "audit-log", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/WrongStack/WrongStack.git --path packages/core/skills/audit-log--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add WrongStack/WrongStack --skill audit-log -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install WrongStack/WrongStack audit-log --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/WrongStack/WrongStack.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/packages/core/skills/audit-log .gemini/skills/audit-log && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "audit-log" agent skill from https://github.com/WrongStack/WrongStack/tree/main/packages/core/skills/audit-log into .gemini/skills/audit-log/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "audit-log", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install WrongStack/WrongStack audit-logInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add WrongStack/WrongStack --skill audit-log -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/WrongStack/WrongStack.git skills-src && mkdir -p .github/skills && cp -r skills-src/packages/core/skills/audit-log .github/skills/audit-log && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "audit-log" agent skill from https://github.com/WrongStack/WrongStack/tree/main/packages/core/skills/audit-log into .github/skills/audit-log/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "audit-log", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add WrongStack/WrongStack --skill audit-log -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install WrongStack/WrongStack audit-log --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/WrongStack/WrongStack.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/packages/core/skills/audit-log .opencode/skills/audit-log && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "audit-log" agent skill from https://github.com/WrongStack/WrongStack/tree/main/packages/core/skills/audit-log into .opencode/skills/audit-log/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "audit-log", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
audit-logA skill your agent uses when analyzing WrongStack session journals to explain what happened in a session — tool usage and failures, token spend and cache efficiency, compactions, delegations, loops…
Audit Log is an agent skill from WrongStack/WrongStack. Use this skill when analyzing WrongStack session journals to explain what happened in a session — tool usage and failures, token spend and cache efficiency, compactions, delegations, loops, and errors. Triggers: user says "audit", "session analysis", "analyze the session", "log analysis", "why did this session cost so much", "token usage", "what went wrong in that run", "usage patterns".
Its SKILL.md is about 1.7k tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file (for example `SKILL.save.md`).
The repository describes itself as: An AI coding agent that reads your code, edits files, runs commands, and reasons through bugs — across a terminal REPL, a full-screen TUI, and a browser UI, while you keep your… The licence is MIT.
6 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit ec76a20. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Shell commands in SKILL.md call:
nodeFrom the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Audit Log loads about 1.7k tokens when it runs. Until then it costs about 100 tokens; SKILL.md has 554 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from WrongStack/WrongStack at commit ec76a20, republished under its MIT licence (© WrongStack). 554 words, ~1,668 tokens.
.claude/skills/audit-log/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.Every WrongStack session is journaled as JSONL: one event per line, in order. The journal is the ground truth for what the agent did, what it cost, and where it went wrong. Analyze it from the file, report numbers that trace back to specific events, and never summarize a session you did not parse.
user_input, tool inputs, and tool results can
hold secrets and personal data; quote only what a finding needs, redacted.~/.wrongstack/projects/<project>/sessions/ (one JSONL per
session).agent_session_linked event in
the parent journal carries the child's agentSessionId and transcriptPath.type | Key fields | Use it for |
|---|---|---|
session_start / session_resumed | id, model, provider | Session identity and starting model |
user_input | content | Turn boundaries; what was asked |
llm_request | model, messageCount, estimatedInputTokens, toolCount | Context growth per request |
llm_response | stopReason, usage, model, provider | Tokens actually billed; stop reasons |
| tool_use | id, name, input | Tool call counts and repeated calls |
tool_result | id, isError, content | Failures — join to tool_use on id |
compaction | before, after, level, reductions | Context pressure |
error | message, phase | Runtime failures |
mode_changed | from, to | Behaviour shifts mid-session |
delegate_started / delegate_completed | target, ok, status, durationMs, toolCalls, costUsd | Delegated work and its outcome |
agent_spawned / agent_stopped / agent_error | agentId, role, reason | Subagent lifecycle |
session_end | usage, pendingToolUses | Final usage; tool calls left unanswered |
usage holds input, output, cacheRead, and cacheWrite (plus
cacheWrite5m / cacheWrite1h when the provider reports them). Journals
written by older versions may lack newer fields; tolerate their absence.
| Question | Computation |
|---|---|
| Which tools failed? | tool_result.isError joined to tool_use.name by id; rate per tool |
| Did it loop? | The same tool_use name and identical input repeated; long runs of calls with no user_input |
| Where did tokens go? | Sum llm_response.usage per turn; growth in llm_request.estimatedInputTokens |
| Is caching working? | cacheRead / (input + cacheRead + cacheWrite) per request; a sudden drop means the prompt prefix changed |
| Was context under pressure? | compaction count, levels, and before → after |
| Did delegation pay off? | delegate_completed ok/status, durationMs, costUsd per target |
| Did it end cleanly? | session_end.pendingToolUses, final stopReason, trailing error events |
Save outside the repository (a temp dir) and run with
node tool-stats.mjs <journal.jsonl>:
import { createReadStream } from 'node:fs';
import { createInterface } from 'node:readline';
const toolById = new Map();
const tools = {};
const tokens = { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 };
const counts = { compaction: 0, error: 0, malformed: 0 };
for await (const line of createInterface({ input: createReadStream(process.argv[2]) })) {
if (!line.trim()) continue;
let event;
try {
event = JSON.parse(line);
} catch {
counts.malformed++;
continue;
}
if (event.type === 'tool_use') {
toolById.set(event.id, event.name);
tools[event.name] ??= { calls: 0, errors: 0 };
tools[event.name].calls++;
} else if (event.type === 'tool_result' && event.isError) {
const name = toolById.get(event.id);
if (name) tools[name].errors++;
} else if (event.type === 'llm_response' && event.usage) {
for (const key of Object.keys(tokens)) tokens[key] += event.usage[key] ?? 0;
} else if (event.type in counts) {
counts[event.type]++;
}
}
console.log(JSON.stringify({ tools, tokens, counts }, null, 2));## Session audit — <session id> (<model>, <start> → <end>)
### Summary
Turns 14 · tool calls 212 (9.4% failed) · tokens in 1.9M / out 48k · cache hit 81% · compactions 2
### Findings
1. The bash tool failed 17/60 calls; 12 are the same `pnpm test` timing out
(tool_use ids …, 10:42–10:58). Cause: watch mode never exits.
2. Cache hit fell from 88% to 12% at 11:03 after mode_changed plan → default;
the prefix changed, and the next 6 requests paid full input price.
### Coverage
Parsed 18,402 lines, 3 malformed and skipped. Subagent transcripts not included.usageobservability — for turning recurring findings into better runtime signalsbug-hunter — for locating the code behind a recurring tool failureoutput-standards — for the <nextsteps> shape in the report© WrongStack, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 1 other file in packages/core/skills/audit-log of WrongStack/WrongStack.
Open the folder on GitHubat commit ec76a20
Audit Log next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Audit Log this skillWrongStack/WrongStack | 368 | — | ~1.7k | Automated safety check: Pass | MIT | |
| Analyzing DNS Logs For Exfiltrationmukul975/Anthropic-Cybersecurity-Skills | 34k | — | ~2.9k | Automated safety check: Pass | Apache-2.0 | |
| Analyze GitHub Action Logswithastro/astro | 63k | 1 repos | ~1.3k | Automated safety check: Pass | Custom licence | |
| Analyzing Windows Event Logs In Splunkmukul975/Anthropic-Cybersecurity-Skills | 34k | — | ~2.8k | Automated safety check: Pass | Apache-2.0 | |
| Analyzing Azure Activity Logs For Threatsmukul975/Anthropic-Cybersecurity-Skills | 34k | — | ~609 | Automated safety check: Pass | Apache-2.0 | |
| Analyzing Security Logs With Splunkmukul975/Anthropic-Cybersecurity-Skills | 34k | — | ~2.5k | Automated safety check: Pass | Apache-2.0 |
mukul975/Anthropic-Cybersecurity-Skills
Analyzes DNS query logs to detect data exfiltration via DNS tunneling, DGA domain communication, and covert C2 channels using entropy analysis, query volume anomalies, and subdomain length detection…
withastro/astro
Analyze recent GitHub Actions workflow runs to identify patterns, mistakes, and improvements.
mukul975/Anthropic-Cybersecurity-Skills
Analyzes Windows Security, System, and Sysmon event logs in Splunk to detect authentication attacks, privilege escalation, persistence mechanisms, and lateral movement using SPL queries mapped to…
mukul975/Anthropic-Cybersecurity-Skills
Queries Azure Monitor activity logs and sign-in logs via azure-monitor-query to detect suspicious administrative operations, impossible travel, privilege escalation, and resource modifications.
mukul975/Anthropic-Cybersecurity-Skills
Leverages Splunk Enterprise Security and SPL (Search Processing Language) to investigate security incidents through log correlation, timeline reconstruction, and anomaly detection.
mukul975/Anthropic-Cybersecurity-Skills
Parses Kubernetes API server audit logs (JSON lines) to detect exec-into-pod, secret access, RBAC modifications, privileged pod creation, and anonymous API access, and builds SIEM detection rules…
WrongStack/WrongStack
Design or substantially improve user-facing interfaces with a product-specific visual direction, content hierarchy, and rendered critique.
WrongStack/WrongStack
A skill your agent uses to audit an interface that already exists and say precisely why it looks generated, templated, or unfinished — a scored rubric across composition, typography, color, states…
WrongStack/WrongStack
A skill your agent uses when external coding agents (Claude Code, Aider, custom scripts) need to participate in the project's shared WrongStack mailbox, or when a user asks to "expose the mailbox"…
WrongStack/WrongStack
A skill your agent uses whenever work can be split across multiple AI agents running in parallel, or when orchestrating leader/worker patterns in WrongStack.
WrongStack/WrongStack
Use this skill before asserting that a CSS, HTML or accessibility capability is available, unavailable, or the right tool — it carries dated, refreshable platform facts and refuses to let stale…
WrongStack/WrongStack
A skill your agent uses when the user wants to communicate with WrongStack's shared project mailbox from outside WrongStack — read messages sent by WrongStack agents, send replies, broadcast to all…
A skill your agent uses when analyzing WrongStack session journals to explain what happened in a session — tool usage and failures, token spend and cache efficiency, compactions, delegations, loops…. Audit Log is an agent skill from WrongStack/WrongStack. Use this skill when analyzing WrongStack session journals to explain what happened in a session — tool usage and failures, token spend and cache efficiency, compactions, delegations, loops, and errors.
Audit Log fits situations like: analyzing WrongStack session journals to explain what happened in a session — tool usage and failures; token spend and cache efficiency.
Run `npx skills add WrongStack/WrongStack --skill audit-log -a claude-code`. Or copy the skill folder (packages/core/skills/audit-log in WrongStack/WrongStack) into .claude/skills/audit-log in your project. Claude Code loads it when a task matches its description.
Run `npx skills add WrongStack/WrongStack --skill audit-log -a codex`. Or copy the skill folder (packages/core/skills/audit-log in WrongStack/WrongStack) into .agents/skills/audit-log in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add WrongStack/WrongStack --skill audit-log -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/audit-log, .gemini/skills/audit-log, .github/skills/audit-log and .opencode/skills/audit-log in your project.
Going by SKILL.md and its folder, Audit Log needs the command-line tools its instructions call (node).
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
Audit Log is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 1.7k tokens (SKILL.md is roughly 6.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Audit Log: Analyzing DNS Logs For Exfiltration (mukul975/Anthropic-Cybersecurity-Skills, 34k stars), Analyze GitHub Action Logs (withastro/astro, 63k stars), Analyzing Windows Event Logs In Splunk (mukul975/Anthropic-Cybersecurity-Skills, 34k stars) and Analyzing Azure Activity Logs For Threats (mukul975/Anthropic-Cybersecurity-Skills, 34k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
WrongStack (a GitHub organization) maintains it in WrongStack/WrongStack, which has 368 GitHub stars. The repository holds 38 skills in this directory. The repository was last updated on October 6, 2026.
Source: WrongStack/WrongStack on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.
