agentmods.dev

bug

bug is a command for coding agents from AleksandarBisevac/claude-plugins. It costs 47 tokens per session (1,256 once invoked), scanned A, original, MIT.

A bug-tracking command built around an audit manifest, a file that records project checks and their status.

In plain words
What is it for?
Use it to add, list, prepare fixes for, and close bugs while tracking their progress from report to resolution.
Why use it?
It keeps reported bugs separate from planned work and requires a failing test first when turning a bug into a fix task; TDD means writing that failing test before the fix.

Command

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the audit plugin — 2 skills, 20 commands, 4 agents, 4 hooks shipped together

not rated 4 3d ago A scan 47 tokens original MIT
View the source file AleksandarBisevac/claude-plugins
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 commands/aleksandarbisevac/claude-plugins/bug
Clone the repo
git clone --depth 1 https://github.com/AleksandarBisevac/claude-plugins

Or install audit, the plugin that ships this one along with the rest of its 2 skills, 20 commands, 4 agents, 4 hooks.

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 bug

README.md
[![agentmods](https://agentmods.dev/badge/commands/aleksandarbisevac/claude-plugins/bug.svg)](https://agentmods.dev/commands/aleksandarbisevac/claude-plugins/bug)
Your own site
<a href="https://agentmods.dev/commands/aleksandarbisevac/claude-plugins/bug"><img src="https://agentmods.dev/badge/commands/aleksandarbisevac/claude-plugins/bug.svg" alt="Measured on agentmods" height="20"></a>
Per session 47 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,256 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 $0.00047 $0.01256
Opus 5 $0.00023 $0.00628
Sonnet 5 $0.00009 $0.00251
Haiku 4.5 $0.00005 $0.00126

Measured 4d ago against content hash e71db8f89de1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 4d 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/audit/commands/bug.md · 73 lines

How it starts

The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/audit:bug — bug tracking on the audit manifest

Bugs live in the manifest's top-level bugs[], OUTSIDE phases — a reported bug is not yet a plan. fix materializes a bug into a tdd task (red-first repro test) that /audit:run executes; the orchestrator flips the bug to fixed when that task commits. Bug lifecycle: open → triaged → in_progress (materialized) → fixed | wontfix.

$ARGUMENTS: first token is the subcommand. Unknown/empty → print usage and stop.

0. Conventions

Read ${CLAUDE_PLUGIN_ROOT}/reference/manifest-conventions.md FIRST. Resolve and read the manifest. If it doesn't exist, stop and point to /audit:init (or the starter template). After EVERY mutation: revalidate with python3 "${CLAUDE_PLUGIN_ROOT}/scripts/manifest/validate-manifest.py" <manifestPath>. The write subcommands (add/fix/close) hold the concurrency lock (see conventions → Concurrency lock) around their writes; list is read-only and never locks.

Subcommand: add "<title>"

  1. If the manifest has no top-level bugs array, create it ("bugs": []) via Edit.
  2. Gather (ask only for what's missing): severity (low/med/high), description, repro (steps, string or array), expected, actual, suspected files (verify with Glob/Grep; empty is allowed).
  3. Allocate BUG-<max existing bug number + 1> and append: {id, title, status: "open", severity, reportedAt: <ISO now>, reportedBy: null, description, repro, expected, actual, files, taskId: null, fixedIn: null, notes: null}.
  4. Revalidate. Report the bug id and the handoff: /audit:bug fix <id> when ready.

Subcommand: list [all|<status>]

Read-only. Print a table id | severity | status | title | taskId | reportedAt. Default filter: everything NOT fixed/wontfix. list all shows everything; list <status> filters to that status. Empty result → say so and point to add.

Subcommand: fix <bugId> [--phase <id>]

  1. Refuse when: the bug doesn't exist; its status is fixed/wontfix; or its taskId is already set and that task is not done → point to /audit:run <taskId> instead (one bug = one live task; no second execution engine).
  2. Target phase: --phase <id> if given (must not be done); else the latest BF<n> phase whose status != done; else CREATE BF<max+1> (title Bugfix batch <n>, the conventions doc's new-phase template, testGate from meta.buildCommands — at minimum the test key).
  3. Materialize the task (new-task template + these specifics):
    • id <phaseId>.<next>; title Fix <bugId>: <bug title>.
    • description embedding the bug's repro / expected / actual verbatim.
    • files = bug's files; bugId: "<bugId>".
    • tests: {mode: "tdd", add: ["repro test that FAILS on current code: <expected> vs <actual>"], expectRedFirst: true, gate: [<phase testGate>]}.
    • risk: bug severity high → high, med → med, else low.
    • model: sonnet (or stronger for risk: "high").
  4. Update the bug: status: "in_progress", taskId: <new task id>.
  5. Extend fileIndex with the task's files. Revalidate.
  6. Report + handoff: Materialized <taskId> for <bugId> — run /audit:run <taskId>. Do NOT execute the fix here — execution, commits, and the red-first check are the /audit:run//audit:phase job (it also flips the bug to fixed + fixedIn on the task commit).

Read the full file on GitHub · 73 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. 4d ago First seen · 73 lines · 47 tokens per session scan A e71db8f89de1

Subscribe to this mod's changes

bug is a command published in the GitHub repository AleksandarBisevac/claude-plugins (4 stars, last pushed 3d ago), licensed MIT. It adds 47 tokens to every session and 1,256 once invoked, about $0.0002 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.

Debuggingagentic-aiauditazure-devopsclaude-codeclaude-code-pluginclaude-code-plugins-marketplace
Related

Other commands, from other repositories

post

Post the current OCR review to a GitHub PR.

spencermarx/open-code-review · 11 tokens

show

Display a past OCR review session.

spencermarx/open-code-review · 7 tokens

history

List past OCR review sessions.

spencermarx/open-code-review · 6 tokens

overlay-apply

Apply NIST 800-53 overlays (FedRAMP, DoD, Privacy, etc.) to existing baselines.

GRCEngClub/claude-grc-engineering · 24 tokens

sdlc

Master orchestrator for the complete 5-phase SDLC pipeline. Runs all phases sequentially with approval gates and handoffs between each phase. Organizes artifacts into handoffs/, docs/, and projects/ directories.

saitarrun/Devforge-ai · 42 tokens

pillar-guidance

Deep dive guidance on DORA's 5 pillars and implementation requirements.

GRCEngClub/claude-grc-engineering · 13 tokens