file-issues

file-issues is a skill for Claude Code, Codex from brazil-bench/pourpoise. It costs 37 tokens per session (7,065 once invoked), scanned A, original, Apache-2.0.

A tool that reads evaluation reports and turns each identified problem or improvement opportunity into a GitHub issue. GitHub issues are tracked tasks attached to a code repository.

In plain words
What is it for?
Use it with Python or Swift/iOS attempt repositories to check reports, verify repository access, and create or preview issues.
Why use it?
It removes the need to copy review findings into separate issues by hand and helps keep every reported shortcoming visible.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is ls ./results/{attempt_repo}.md.

Good fit Use it with Python or Swift/iOS attempt repositories to check reports, verify repository access, and create or preview issues.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/brazil-bench/pourpoise
agentmods
npx agentmods add skills/brazil-bench/pourpoise/file-issues

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 file-issues

README.md
[![agentmods](https://agentmods.dev/badge/skills/brazil-bench/pourpoise/file-issues/github.svg)](https://agentmods.dev/skills/brazil-bench/pourpoise/file-issues)
Your own site
<a href="https://agentmods.dev/skills/brazil-bench/pourpoise/file-issues"><img src="https://agentmods.dev/badge/skills/brazil-bench/pourpoise/file-issues/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 file-issues

Your own site · 80×15
<a href="https://agentmods.dev/skills/brazil-bench/pourpoise/file-issues"><img src="https://agentmods.dev/badge/skills/brazil-bench/pourpoise/file-issues.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 7,065 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.
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 $0.00037 $0.07065
Opus 5 $0.00018 $0.03533
Sonnet 5 $0.00007 $0.01413
Haiku 4.5 $0.00004 $0.00707

Measured 9d ago against content hash b07875f5c1ee, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

file-issues 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.

skills/file-issues/SKILL.md · 1,084 lines

How it starts

The opening of the file, as written. The whole thing — 1,084 lines — stays where its author put it; the contents beside it link to each section on GitHub.

File Issues from Evaluation

Overview

This SOP parses evaluation reports from brazil-bench attempts and creates individual GitHub issues on each attempt's repository for every shortcoming, warning, or improvement opportunity identified during the review.

Parameters

  • attempt_repo (required): Repository name (e.g., 2025-12-13-python-claude-hive)
  • evaluation_path (optional, default: ./results/{attempt_repo}.md): Path to evaluation report
  • dry_run (optional, default: false): If true, show issues that would be created without creating them

Steps

1. Load Evaluation Report

Read the evaluation report for the specified attempt.

Constraints:

  • You MUST verify the evaluation report exists before proceeding
  • You MUST parse markdown sections to identify shortcomings
  • You MUST NOT proceed if the report is missing or malformed
# Verify report exists
ls ./results/{attempt_repo}.md

# Read the report content
cat ./results/{attempt_repo}.md

2. Verify Repository Access

Confirm the attempt repository exists and is writable.

Constraints:

  • You MUST verify the repo exists on GitHub
  • You MUST check that issues are enabled on the repo
  • You SHOULD check for existing issues to avoid duplicates
  • You SHOULD use default GitHub labels (no custom labels required)
# Verify repo exists
gh repo view brazil-bench/{attempt_repo}

# List existing issues to check for duplicates
gh issue list -R brazil-bench/{attempt_repo} --limit 100

# List available labels (use default GitHub labels)
gh label list -R brazil-bench/{attempt_repo}

Default GitHub Labels to Use:

Issue Type Default Label Reason
Missing requirement enhancement It's a feature that needs to be added
Test quality issue bug Tests not working as expected
Compliance summary enhancement Tracking improvements needed
Quality concern enhancement Code improvement request
Documentation gap documentation Missing or incomplete docs

Read the full file on GitHub · 1,084 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 · 1,084 lines · 37 tokens per session scan A b07875f5c1ee

Subscribe to this mod's changes

file-issues is a skill published in the GitHub repository brazil-bench/pourpoise (11 stars, last pushed 7mo ago), licensed Apache-2.0. It adds 37 tokens to every session and 7,065 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 2026-08-30.

Related

Other skills, from other repositories