compare_tasks

compare_tasks is a skill for Claude Code, Codex from Bilal140202/the-lord-of-the-skills. It costs 15 tokens per session (2,429 once invoked), scanned A, a copy of compare-tasks, MIT.

A guide for comparing two Harbor benchmark runs on the same task. Harbor is a system for running and evaluating coding-agent tasks.

In plain words
What is it for?
Use it to locate the matching trial data, compare headline results, inspect logs and outputs, and identify the cause of a performance difference.
Why use it?
It helps explain why two runs produced different results instead of only showing that their scores differ.

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 ./evals/harbor/cmd.py task "$RUN_A" "$TASK".

Good fit Use it to locate the matching trial data, compare headline results, inspect logs and outputs, and identify the cause of a performance difference.

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/Bilal140202/the-lord-of-the-skills
agentmods
npx agentmods add skills/bilal140202/the-lord-of-the-skills/block__goose

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 compare_tasks

README.md
[![agentmods](https://agentmods.dev/badge/skills/bilal140202/the-lord-of-the-skills/block__goose/github.svg)](https://agentmods.dev/skills/bilal140202/the-lord-of-the-skills/block__goose)
Your own site
<a href="https://agentmods.dev/skills/bilal140202/the-lord-of-the-skills/block__goose"><img src="https://agentmods.dev/badge/skills/bilal140202/the-lord-of-the-skills/block__goose/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 compare_tasks

Your own site · 80×15
<a href="https://agentmods.dev/skills/bilal140202/the-lord-of-the-skills/block__goose"><img src="https://agentmods.dev/badge/skills/bilal140202/the-lord-of-the-skills/block__goose.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 15 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,429 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 100% copy Near-identical to another mod 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 $0.00015 $0.02429
Opus 5 $0.00008 $0.01215
Sonnet 5 $0.00003 $0.00486
Haiku 4.5 $0.00002 $0.00243

Measured 9d ago against content hash 0767032710f4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

compare_tasks 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.

Origin

This is a copy

100% identical to compare-tasks — 2 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

skills/gondor/claude-code/block__goose/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.

Compare two harbor runs on one task

Use when given two harbor run names and a task name, and the goal is to understand why the two runs differ on that task — not just that they differ.

Inputs

  • RUN_A: harbor run name (e.g. sonnet46-full)
  • RUN_B: harbor run name (e.g. pi-sonnet46-full)
  • TASK: bare task name (e.g. extract-elf, not terminal-bench/extract-elf)
  • RUNS_DIR: defaults to evals/harbor/runs/ relative to the repo root

Procedure

1. Find each run's trial directory for the task

Harbor 0.8 names trial dirs <task>__<random-suffix> (e.g. extract-elf__bU3GHs4), not <task>.1. The suffix is unique per trial, so don't guess it — discover it from disk:

TRIAL_A_DIR=$(ls -d "$RUNS_DIR/$RUN_A/${TASK}__"*/ 2>/dev/null | head -1)
TRIAL_B_DIR=$(ls -d "$RUNS_DIR/$RUN_B/${TASK}__"*/ 2>/dev/null | head -1)

If either is empty, that run didn't include this task — stop and say so. (ls "$RUNS_DIR/$RUN_A/" shows what's there.)

If you want to confirm the match, every result.json carries task_name and trial_name:

jq '{task_name, trial_name}' "$TRIAL_A_DIR/result.json"

2. Headline facts

The fastest path is to let cmd.py task do it for you — it already prints status, reward, duration, tokens, turns, cost, error class, and the tail of the verifier stdout:

./evals/harbor/cmd.py task "$RUN_A" "$TASK"
./evals/harbor/cmd.py task "$RUN_B" "$TASK"

Only drop to raw jq against result.json if you need a field cmd.py task doesn't print. The actual shape (harbor 0.8 TrialResult):

jq '{
  reward: (.verifier_result.rewards.reward
           // (.verifier_result.rewards | to_entries | .[0].value)
           // null),
  rewards_all: .verifier_result.rewards,
  duration_seconds: ((.finished_at | fromdateiso8601) - (.started_at | fromdateiso8601)),
  input_tokens: .agent_result.n_input_tokens,
  cache_tokens: .agent_result.n_cache_tokens,
  output_tokens: .agent_result.n_output_tokens,
  cost_usd: .agent_result.cost_usd,
  error_type: .exception_info.exception_type,
  error_message: (.exception_info.exception_message // "" | split("\n")[0])
}' "$TRIAL_A_DIR/result.json"

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. 9d ago First seen · 228 lines · 15 tokens per session scan A 0767032710f4

Subscribe to this mod's changes

compare_tasks is a skill published in the GitHub repository Bilal140202/the-lord-of-the-skills (4 stars, last pushed 6d ago), licensed MIT. It adds 15 tokens to every session and 2,429 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to compare-tasks, differing in 2 lines, and is treated as a copy.

Related

Other skills, from other repositories

serpsmith

Publish SEO articles reliably across AI-agent runtimes.

emiliojohann/SERPsmith · 14 tokens

tool-calling-tutor

Use when a tool-calling agent does not call a tool, sends wrong arguments, loops without stopping, or needs a function schema. Guides a four-branch diagnosis and five-step schema repair. Do not use for framework-specific, MCP-server, or production-observability questions.

WenyuChiou/awesome-agentic-ai-zh · 62 tokens

performing-threat-hunting-with-yara-rules

Use YARA pattern-matching rules to hunt for malware, suspicious files, and indicators of compromise across filesystems and memory dumps. Covers rule authoring, yara-python scanning, and integration with threat intel feeds.

adriannoes/awesome-agentic-ai · 53 tokens

hunt-idor

Hunting skill for idor vulnerabilities. Built from 26 public bug bounty reports. Use when hunting idor on any target.

adriannoes/awesome-agentic-ai · 30 tokens

performing-soc2-type2-audit-preparation

Automates SOC 2 Type II audit preparation including gap assessment against AICPA Trust Services Criteria (CC1-CC9), evidence collection from cloud providers and identity systems, control testing validation, remediation tracking, and continuous compliance monitoring. Covers all five TSC categories (Security…

adriannoes/awesome-agentic-ai · 112 tokens

testrail

Sync tests with TestRail. Use when user mentions "testrail", "test management", "test cases", "test run", "sync test cases", "push results to testrail", or "import from testrail".

adriannoes/awesome-agentic-ai · 50 tokens