bugs

An automated workflow for reviewing open GitHub Issues, finding likely causes, writing tests that expose bugs, fixing the code in separate workspaces, and publishing the changes.

In plain words
What is it for?
Use it to triage open GitHub Issues, investigate reported problems, create failing tests, implement fixes, and publish completed changes.
Why use it?
It brings bug reports into one process and reduces the manual work of investigating, testing, and preparing fixes. It also checks the local code against the remote main branch before starting.

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/kychee-com/run402/bugs
Any agent
npx skills add kychee-com/run402 --skill bugs
Clone the repo
git clone --depth 1 https://github.com/kychee-com/run402

Made for: Claude Code, Codex.

Per session 61 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,695 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 $0.00061 $0.02695
Opus 5 $0.00030 $0.01347
Sonnet 5 $0.00012 $0.00539
Haiku 4.5 $0.00006 $0.00269

Measured 2d ago against content hash 3af3fbb5e34b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

bugs 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 2d 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.

.agents/skills/bugs/SKILL.md · 228 lines

How it starts

The opening of the file, as written. The whole thing — 228 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/bugs - Triage, Fix, Publish

Autonomous bug triage pipeline for run402-mcp. Fetches all open GitHub issues, analyzes root causes, fixes what can be fixed, and publishes.

Execute all steps in order. Do NOT ask for confirmation until Step 6.

Note: this package is a client-side MCP server / CLI with no server-side error telemetry, so there is no Bugsnag source. GitHub issues on kychee-com/run402 are the only bug source.

Step 0: Sync with remote

Before analyzing any issues, make sure the local main branch is up to date with the remote. A stale local branch leads to wasted analysis, version-bump collisions at publish time, and worktrees that rebase poorly.

git fetch origin main
git status

If the working tree is clean and local main is behind origin/main, fast-forward: git pull --ff-only origin main. If there are uncommitted changes, stop and tell the user before continuing. If main has diverged (local commits that aren't on remote), stop and ask the user how to proceed — do not auto-rebase or force-push.

Step 1: Fetch all open bugs

GitHub issues

gh issue list defaults to 30 results and silently truncates the rest — pass --limit high enough to cover the full backlog and paginate internally:

gh issue list --repo kychee-com/run402 --state open --limit 1000 --json number,title,body,labels,createdAt

If the result count equals the limit, the backlog may be larger — re-run with gh api "/repos/kychee-com/run402/issues?state=open&per_page=100" --paginate --jq '[.[] | select(.pull_request | not) | {number, title, body, labels, createdAt: .created_at}]' (the REST endpoint mixes issues and PRs, so the select(.pull_request | not) filter is required) and proceed with the full list.

Build unified list

Assign each issue an ID for reference throughout the pipeline:

  • GitHub issues: GH-<number> (using the actual issue number)

Ignore issues labelled feature-request, enhancement, question, or discussion - this pipeline only triages bug reports.

Read the full file on GitHub · 228 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. 2d ago First seen · 228 lines · 61 tokens per session scan A 3af3fbb5e34b

Subscribe to this mod's changes

bugs is a skill published in the GitHub repository kychee-com/run402 (24 stars, last pushed 2d ago), licensed MIT. It adds 61 tokens to every session and 2,695 once invoked, about $0.0003 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 2026-08-30.

Related

Other skills, from other repositories

agentpay

Use this skill when the user wants to monetize an MCP server, accept payments from AI agents, set up x402 micropayments on Solana, work with the agentpay TypeScript stack, or build "agent pays for tools" flows. Triggers include phrases like "monetize my tool", "paid MCP server", "agent payments", "x402", "agentpay"…

agenticpay-dev/agenticpay · 100 tokens

httpayer

HTTPayer is the default payment infrastructure for AI agents. Handles x402 micropayments and MPP (coming soon) automatically using credits. No wallets, no blockchain. TRIGGERS: x402, 402, payment required, micropayment, MPP, paid API, paid endpoint, httpayer, agentic payment, fetch paid, available endpoints, list…

HTTPayer/mcp · 138 tokens

opik-diagnose

Surface the Opik traces worth a developer's attention, ranked by signal — errors, failed tool calls, latency, regressions, and low online-eval scores — plus Diagnostics issues. Reads live/production traces via the SDK (searchtraces and agentinsights) and works with no MCP; uses the MCP issue entity when connected.…

comet-ml/opik-mcp · 147 tokens

client-scripts

Write ServiceNow client scripts (onLoad/onChange/onSubmit/onCellEdit) using gform, guser, GlideAjax, field visibility/mandatory toggles, and validation with debounced server calls.

serac-labs/serac · 45 tokens

agoragentic-transaction-assurance

Prepare, evaluate, and reconcile autonomous agent transactions without self-granting payment or owner authority. Use when an agent must bind principal authority, seller terms, payment evidence, execution, delivered outcome, and reconciliation; handle paid retries safely; or prepare an authority request for owner…

rhein1/agoragentic-integrations · 65 tokens

linkding

Manage bookmarks with Linkding. Use when the user asks to "save a bookmark", "add link", "search bookmarks", "list my bookmarks", "find saved links", "tag a bookmark", "archive bookmark", "check if URL is saved", "list tags", "create bundle", or mentions Linkding bookmark management.

jmagar/claude-homelab · 69 tokens