agent-bug

agent-bug is a skill for Claude Code, Codex from leviuszen/meaning-assurance. It costs 17 tokens per session (567 once invoked), scanned A, original, Apache-2.0.

An evidence-based record for tracking confirmed bugs found during Agent Workbench tasks, reviews, tests, or manual checks.

In plain words
What is it for?
Record one concrete bug at a time with evidence, affected files, reproduction steps, and the expected and actual results.
Why use it?
It keeps unresolved defects specific, reproducible, and separate from vague warnings or issues that have already been fixed.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Codex.

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/leviuszen/meaning-assurance/agent-bug
Any agent
npx skills add leviuszen/meaning-assurance --skill agent-bug
Clone the repo
git clone --depth 1 https://github.com/leviuszen/meaning-assurance

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-bug

README.md
[![agentmods](https://agentmods.dev/badge/skills/leviuszen/meaning-assurance/agent-bug.svg)](https://agentmods.dev/skills/leviuszen/meaning-assurance/agent-bug)
Your own site
<a href="https://agentmods.dev/skills/leviuszen/meaning-assurance/agent-bug"><img src="https://agentmods.dev/badge/skills/leviuszen/meaning-assurance/agent-bug.svg" alt="Measured on agentmods" height="20"></a>
Per session 17 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 567 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 5.1 $0.00017 $0.00567
Opus 5 $0.00009 $0.00283
Sonnet 5 $0.00003 $0.00113
Haiku 4.5 $0.00002 $0.00057

Measured 6d ago against content hash 67ee47581ee7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

agent-bug 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 6d 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.

skills/agent-bug/SKILL.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Bug

Use this skill when Codex needs to record a concrete bug found during Agent Workbench work, external-agent review, result collection, dry runs, tests, or manual inspection.

When To Record

  • A test fails and the failure is not immediately fixed in the same step.
  • External review reports a concrete defect with evidence.
  • Collect-AgentResult.ps1 shows a blocking issue or bug-like signal that Codex confirms is a real defect.
  • A manual dry run reveals a repeatable failure.

Rules

  • Codex remains the primary conversation and final reviewer.
  • Prefer evidence over interpretation: include command output, file paths, reproduction steps, and expected versus actual behavior.
  • Keep each bug record focused on one defect.
  • Do not record vague, duplicate, or secret-containing entries.
  • Do not paste API keys, provider config, tokens, private launcher contents, or secret-like text into bug fields.
  • Do not treat result collection warnings as automatic bugs; Codex decides whether to register one.

Create A Bug

Run New-AgentBug.ps1 from the installed workbench scripts:

$WorkbenchRoot = $env:AGENT_WORKBENCH_HOME
& (Join-Path $WorkbenchRoot "scripts\New-AgentBug.ps1") `
-WorkbenchRoot $WorkbenchRoot `
  -Slug "short-bug-slug" `
  -Severity medium `
  -Source codex `
  -Summary "Short concrete bug summary." `
  -Evidence "Relevant command output, file reference, or review evidence." `
  -Reproduction "Steps or command that triggers the issue." `
  -ExpectedBehavior "What should have happened." `
  -ActualBehavior "What happened instead." `
  -SuggestedFix "Optional focused fix direction."

Use the narrowest accurate Severity and Source values supported by the script.

Collect Bugs

Summarize the current ledger:

$WorkbenchRoot = $env:AGENT_WORKBENCH_HOME
& (Join-Path $WorkbenchRoot "scripts\Collect-AgentBugs.ps1") `
-WorkbenchRoot $WorkbenchRoot

Filter by state when needed:

$WorkbenchRoot = $env:AGENT_WORKBENCH_HOME
& (Join-Path $WorkbenchRoot "scripts\Collect-AgentBugs.ps1") `
-WorkbenchRoot $WorkbenchRoot `
  -State open

Read the full file on GitHub · 69 lines

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 · 69 lines · 17 tokens per session scan A 67ee47581ee7

Subscribe to this mod's changes

agent-bug is a skill published in the GitHub repository leviuszen/meaning-assurance (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 17 tokens to every session and 567 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

build-test

Run the project's build / typecheck / lint / test commands and emit the build.passing + tests.passing signals devloop convergence reads.

nexu-io/open-design · 31 tokens

patch-edit

Apply one rewrite-plan step at a time as small reviewable file edits, never rewriting whole files when a localised change suffices.

nexu-io/open-design · 30 tokens

org2-performance-guard

Prevent CPU, RAM, I/O, background-work, and false-green lifecycle regressions in ORG2. Use when adding or reviewing polling, timers, Realtime subscriptions, event listeners, workers, streaming paths, caches, pagination, provider-owned transcript ingestion or identity/dedupe, external-history scans, cloud sync…

org2AI/ORG2 · 112 tokens

memtrace-first

Route code discovery, debugging, flow tracing, how-code-works questions, and pre-edit rationale checks in indexed source-code repos to Memtrace graph plus Cortex decision tools. Use first before searching/reading code, and before editing, refactoring, deleting, or re-picking an approach that may have a recorded…

syncable-dev/memtrace-public · 115 tokens

memtrace-incident-investigation

Investigate source-code bugs, incidents, regressions, production issues, and failures to root cause with Memtrace symbol search, impact, call graph, and temporal history. Use when the user asks about root cause analysis, what broke, or what changed when debugging a failure. Do not start with Grep, Glob, rg, find, or…

syncable-dev/memtrace-public · 99 tokens

memtrace-preflight

Run a one-call pre-flight check on a single existing symbol before editing it: blast radius, co-change partners, complexity, 30-day churn, and verification checklist, then check Cortex decision memory for rationale/bans when intent may matter. Use before modifying any existing function or symbol you did not just…

syncable-dev/memtrace-public · 102 tokens