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.
git clone --depth 1 https://github.com/brazil-bench/pourpoisenpx agentmods add skills/brazil-bench/pourpoise/file-issuesWrote 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.
[](https://agentmods.dev/skills/brazil-bench/pourpoise/file-issues)<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.
<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>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.
| Model | Per session | Once 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 |
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.
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 |
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.
- 9d ago First seen · 1,084 lines · 37 tokens per session scan A b07875f5c1ee
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.
Other skills, from other repositories
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
story-readiness
Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…
autotask-creator
Rules for automation CRUD from the group-chat commander. The commander does not call mutation tools and does not edit cloud/autotasks files directly. It emits one or more top-level ... containers in its final text; the bus parses and applies them after the turn.
remove
Remove a deployed framework or addon from the current workspace.