bug-audit

A recurring multi-agent audit for serious software bugs, especially problems that corrupt data, lose data, or silently report incorrect results. It checks the relevant changes and several known high-risk areas of the TokenTelemetry project.

In plain words
What is it for?
Use it for a weekly bug sweep covering silent limits, incomplete results, stored-state integrity, stale data, timestamp calculations, and trust boundaries.
Why use it?
It focuses review effort on failures that can damage trust or persisted information rather than on style issues or unlikely hypotheticals. Confirmed serious findings can be tracked as GitHub issues.

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/vasihemanth/tokentelemetry/bug-audit
Any agent
npx skills add VasiHemanth/tokentelemetry --skill bug-audit
Clone the repo
git clone --depth 1 https://github.com/VasiHemanth/tokentelemetry

Made for: Claude Code, Codex.

Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,018 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 $0.00000 $0.01018
Opus 5 $0.00000 $0.00509
Sonnet 5 $0.00000 $0.00204
Haiku 4.5 $0.00000 $0.00102

Measured yesterday against content hash f5c43c088ec8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

bug-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.

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.

.claude/skills/bug-audit/SKILL.md · 81 lines

How it starts

The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.

bug-audit — weekly serious-bug sweep

Multi-agent audit of the TokenTelemetry backend/frontend for the bug class that motivated it (PR #131: a silent 100-session cap plus stub rows crushing real persisted data). Optimized for bugs that corrupt data, lose data, or silently report wrong numbers — not style or hypotheticals.

Scope selection (do this first)

  1. Find the last audit marker: the most recent GitHub issue labeled bug-audit (gh issue list --label bug-audit --state all --limit 1), whose body records the commit it audited up to.
  2. Primary scope = git diff <last-audited-commit>..HEAD plus any file those diffs touch. If no marker exists (first run), scope = backend/*.py and frontend/src/lib + frontend/src/app.
  3. Always include the standing hot-spots regardless of diff: backend/main.py scan loops, backend/history_store.py, backend/scan_cache.py (if present), anything matching backend/*cache*/backend/*store*.

Fan-out (Agent tool; run each wave's spawns in parallel)

Wave 1 — breadth, audit-scanner (Sonnet), one per dimension:

  • silent caps & truncation (slices, LIMIT, early breaks, [:N])
  • persisted-state integrity (upserts that overwrite, absent-vs-zero confusion, stub/partial rows)
  • cache & staleness (mtime keys, missing version fields, invalidation gaps)
  • timestamp/timezone math (naive datetimes, mtime-as-date, day bucketing)
  • trust boundaries (on-disk ids/paths/cwd used in paths, SQL, shell)
  • token/cost arithmetic (double counting, high-water-mark vs sum, unit slips)

Give each scanner the scope file list and its dimension. Prompt them to return the FINDING-block format their agent definition specifies.

Wave 2 — depth, audit-deep (Opus), in the same parallel batch as wave 1: one per risky subsystem actually present in scope, typically 2-4 of:

  • scan → cache → history-upsert pipeline (the PR #131 path)
  • one agent-store parser that changed recently (Claude, Codex, Copilot…)
  • any new persisted format introduced since the last audit
  • the analytics aggregation path (/analytics, ecosystem rollups)

Read the full file on GitHub · 81 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. yesterday First seen · 81 lines · 0 tokens per session scan A f5c43c088ec8

Subscribe to this mod's changes

bug-audit is a skill published in the GitHub repository VasiHemanth/tokentelemetry (340 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,018 tokens. 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 2026-08-30.

Related

Other skills, from other repositories

browser-use

Drive agentglass's built-in browser — the one already signed in to the sites this project uses. Use when a task needs a page behind a login (a dashboard, a ticket, a staging app), when a URL fetched with curl comes back signed out or JavaScript-rendered, or when the user asks you to look at, click through, or…

SirAllap/agentglass · 80 tokens

go-rig

Use this skill when building, reviewing, or refactoring Go code that must follow strict design discipline — ATDD/TDD workflow, explicit dependency injection, package-boundary discipline, and structured code review. Complements CLAUDE.md by focusing on process and design judgment rather than version-specific Go…

mudrii/openclaw-dashboard · 64 tokens

frontend-dashboard

Use this skill when editing the embedded dashboard frontend in this repository. It focuses on preserving the single-file embedded SPA model, keeping the UI lightweight, and avoiding unnecessary frontend tooling or dependencies.

mudrii/openclaw-dashboard · 40 tokens

go-review

Use this skill when the task is to review Go code in this repository. Focus on bugs, regressions, API compatibility, test gaps, concurrency risks, and violations of the zero-dependency and root-facade constraints.

mudrii/openclaw-dashboard · 48 tokens

project-ops

Use this skill when working on repository operations in this project, including build, test, lint, release, CI alignment, Makefile-driven checks, and operational packaging constraints.

mudrii/openclaw-dashboard · 38 tokens

git-commit-helper

Generates meaningful git commit messages for Spec-Driven Development workflows. Use when creating commits, suggesting commit messages, or helping with task-based version control. Automatically links commits to work packages.

korjwl1/toki-monitor · 42 tokens