bifrost: Skill for Claude Code

.claude/skills/investigate-issue/SKILL.md

investigate-issue is a skill for Claude Code from maximhq/bifrost. It costs 78 tokens per session (8,645 once invoked), scanned A, original, Apache-2.0.

A workflow for investigating a GitHub issue, a reported bug or requested change in a code project. It examines the issue, relevant code, documentation, possible effects, and tests.

In plain words
What is it for?
Triaging issues, researching their cause, planning fixes, checking side effects, and defining regression tests. For bugs, TDD means writing and showing a failing test before approving the fix.
Why use it?
It turns a broad issue report into a concrete implementation plan and identifies what must be tested before changes are made.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: names the AskUserQuestion tool; positional $N argument; mentions AGENTS.md.

This is maximhq/bifrost's own configuration. It tells Claude Code how to work on bifrost itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything bifrost configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is cd ui && ./node_modules/.bin/vitest related <changed-file> --run.

About the project

Bifrost is an AI gateway that gives applications one OpenAI-compatible API for accessing models from more than 23 providers. It is used to route model requests, handle provider failover and load balancing, and apply features such as caching, guardrails, and MCP gateway support.

maximhq/bifrost · 7,913 stars · on GitHub · getmaxim.ai

Reuse

Borrowing it

Nothing to install: this file belongs to maximhq/bifrost. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/maximhq/bifrost/dev/.claude/skills/investigate-issue/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/maximhq/bifrost

Made for: Claude Code.

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 investigate-issue

README.md
[![agentmods](https://agentmods.dev/badge/skills/maximhq/bifrost/investigate-issue/github.svg)](https://agentmods.dev/skills/maximhq/bifrost/investigate-issue)
Your own site
<a href="https://agentmods.dev/skills/maximhq/bifrost/investigate-issue"><img src="https://agentmods.dev/badge/skills/maximhq/bifrost/investigate-issue/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for investigate-issue

Your own site · 80×15
<a href="https://agentmods.dev/skills/maximhq/bifrost/investigate-issue"><img src="https://agentmods.dev/badge/skills/maximhq/bifrost/investigate-issue.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 78 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 8,645 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 2 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Excessive Agency · line 391
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
  • medium MCP Rug Pull · line 497
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
How audits are shown
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 $0.00078 $0.08645
Opus 5 $0.00039 $0.04322
Sonnet 5 $0.00016 $0.01729
Haiku 4.5 $0.00008 $0.00864

Measured 9d ago against content hash 5be4efa3fe0c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

investigate-issue 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 9d 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.

.claude/skills/investigate-issue/SKILL.md · 849 lines

How it starts

The opening of the file, as written. The whole thing — 849 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Investigate GitHub Issue

Fetch a GitHub issue, analyze the report, search the codebase for relevant code, research external documentation, and present a comprehensive implementation plan with side-effect analysis and test guidance.

Your final report MUST contain all of these sections:

  1. Issue Details (from Step 1)
  2. Classification (from Step 2)
  3. Codebase Analysis + Documentation Research (from Step 3, including sub-step 3e)
  4. Impact Analysis (from Step 4)
  5. Test Plan (from Step 5)
  6. Regression Rerun Scope (from Step 5e) -- which existing tests must rerun, and why
  7. TDD: Failing Tests (from Step 5f) -- Bug issues only: the test source AND the actual red output from the applicable Makefile recipe, pasted verbatim, BEFORE asking to implement
  8. Full Presentation (Step 6 template)

If any section is missing, go back and complete it before presenting the report.

For Bug issues the approval gate is NOT "may I write a test?" -- the failing test is already written and shown to be red. The gate is "may I write the fix?"

Usage

/investigate-issue <ISSUE_ID>           # Investigate issue by number
/investigate-issue                      # Prompts for issue ID

Workflow Overview

  1. Get the issue -- Fetch full issue details from GitHub
  2. Classify the issue -- Determine type (bug, feature, docs) and affected areas
  3. Search the codebase and research docs -- Find relevant code, then research the libraries it depends on via Context7 and WebSearch
  4. Analyze impact -- Cross-reference codebase findings with documentation to identify side effects, dependencies, and breaking changes
  5. Suggest tests -- If changes touch core/, recommend specific LLM and MCP test additions 5b. Scope the reruns -- Use coverage to determine which existing tests exercise the lines you plan to change, and tier them by necessity 5c. Go red (Bug issues) -- Write the regression test(s) and run them to confirm failure for the right reason, BEFORE presenting the plan
  6. Present the plan -- Show findings, the red test output, the rerun scope, and the recommended fix
  7. Implement with approval -- After approval, apply the fix and show red-to-green

Read the full file on GitHub · 849 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. 9d ago First seen · 849 lines · 78 tokens per session scan A 5be4efa3fe0c

Subscribe to this mod's changes

investigate-issue is a skill published in the GitHub repository maximhq/bifrost (7,913 stars, last pushed today), licensed Apache-2.0. It adds 78 tokens to every session and 8,645 once invoked, about $0.0004 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

new-project

Bootstrap a new product repository for agentic development. Use when starting a new app, empty repo, greenfield project, or when the user asks to stand up the factory, the start loop, or what to install before the first feature.

sergenes/mini_agent · 51 tokens

agent-merge-conflict-arbiter

Neutral arbiter for merge conflicts between two agents.

NousResearch/hermes-agent · 19 tokens

agentcore-investigation

Investigate Bedrock AgentCore runtime sessions via CloudWatch Logs Insights — resolve session/trace IDs, query OTEL spans, filter noise, build timelines. Use when debugging AgentCore agent sessions, tracing tool calls, or analyzing latency.

awslabs/mcp · 52 tokens

code-task

PREFERRED way to change code in a REAL repository: fix a GitHub issue, fix a bug, add/implement a function or feature, or make any edit to a project the user names by a filesystem path (e.g. /tmp/foo, /code/bar) or a git URL. Clones the repo, runs an OpenSquilla agent on the host to make the change on a task branch…

opensquilla/opensquilla · 322 tokens

mantis-critic

Assesses the production viability of findings, filtering out debug-only features and assertion traps. Use when findings have been validated and you need to confirm they are triggerable in production release builds (with assertions disabled). Don't use for writing reproduction scripts or patches.

google/mantis · 55 tokens

explain-issue

Explain a GitHub issue: the background problem and the proposed solution.

dyoshikawa/rulesync · 18 tokens