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/re-evaluateWrote 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/re-evaluate)<a href="https://agentmods.dev/skills/brazil-bench/pourpoise/re-evaluate"><img src="https://agentmods.dev/badge/skills/brazil-bench/pourpoise/re-evaluate/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/re-evaluate"><img src="https://agentmods.dev/badge/skills/brazil-bench/pourpoise/re-evaluate.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 | $0.00031 | $0.03572 |
| Opus 5 | $0.00015 | $0.01786 |
| Sonnet 5 | $0.00006 | $0.00714 |
| Haiku 4.5 | $0.00003 | $0.00357 |
Grade A, and why
re-evaluate 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 — 494 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Re-Evaluate Attempt After Changes
Overview
This SOP monitors attempt repositories for closed issues and code changes, re-runs relevant evaluations, updates the main evaluation report, and files new issues for any regressions or newly discovered problems.
Parameters
- attempt_repo (required): Repository name (e.g.,
2025-12-13-python-claude-hive) - evaluation_path (optional, default:
./results/{attempt_repo}.md): Path to existing evaluation report - full_reeval (optional, default:
false): If true, run complete evaluation instead of targeted checks
Steps
1. Check Repository for Changes
Determine if the repository has changed since the last evaluation.
Constraints:
- You MUST check for new commits since last evaluation
- You MUST identify closed issues that triggered changes
- You MUST NOT proceed if no changes detected (unless full_reeval=true)
# Navigate to existing clone or re-clone
cd ./reviews/{attempt_repo} || gh repo clone brazil-bench/{attempt_repo} ./reviews/{attempt_repo}
# Fetch latest changes
git fetch origin
# Check for new commits on main/master
git log HEAD..origin/main --oneline 2>/dev/null || git log HEAD..origin/master --oneline
# Pull latest changes
git pull origin main 2>/dev/null || git pull origin master
# Get the latest commit info
git log -1 --format="%H %ai %s"
2. Identify Closed Issues
List issues that have been closed since the last evaluation.
Constraints:
- You MUST fetch all closed issues from the repo
- You MUST categorize issues by type ([Missing], [Test Quality], [Docs], etc.)
- You SHOULD note which issues were addressed vs closed without fix
# List all closed issues
gh issue list -R brazil-bench/{attempt_repo} --state closed --json number,title,closedAt,labels
# Get details of recently closed issues
gh issue list -R brazil-bench/{attempt_repo} --state closed --limit 20 --json number,title,body,closedAt
# Check issue comments for resolution notes
gh issue view {issue_number} -R brazil-bench/{attempt_repo} --json comments
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 · 494 lines · 31 tokens per session scan A c0557955524f
re-evaluate is a skill published in the GitHub repository brazil-bench/pourpoise (11 stars, last pushed 7mo ago), licensed Apache-2.0. It adds 31 tokens to every session and 3,572 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
adversarial-reviewer
Adversarial code review that assumes bugs exist and hunts for them. Use when asked to review code, find bugs, audit for correctness, stress-test a PR, or when someone says "tear this apart" or "what's wrong with this". Give no benefit of the doubt — every line is guilty until proven innocent.
go-testing
Trigger: Go tests, go test coverage, Bubbletea teatest, golden files. Apply focused Go testing patterns.
semgrep-rule-variant-creator
Creates language variants of existing Semgrep rules. Use when porting a Semgrep rule to specified target languages. Takes an existing rule and target languages as input, produces independent rule+test directories for each language.
brooks-sweep
Full-sweep mode: runs a unified analysis across all quality dimensions — code decay, architecture, tech debt, and test quality — then applies fixes directly to the codebase. Safe changes are auto-applied; risky changes are confirmed before execution. Drawing on twelve classic engineering books. Triggers when: user…
include-test-files-that-assert-on-behavior-being-changed-in-decl
When delegating a task affected by this skill, include.
plugin-review
Review plugin quality with tiered checks and dependency scoping. Use for PR and pre-release audits.