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/Kastalien-Research/thoughtboxnpx agentmods add skills/kastalien-research/thoughtbox/workflow-tournamentWrote 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/kastalien-research/thoughtbox/workflow-tournament)<a href="https://agentmods.dev/skills/kastalien-research/thoughtbox/workflow-tournament"><img src="https://agentmods.dev/badge/skills/kastalien-research/thoughtbox/workflow-tournament/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/kastalien-research/thoughtbox/workflow-tournament"><img src="https://agentmods.dev/badge/skills/kastalien-research/thoughtbox/workflow-tournament.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
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 →
- high Privilege Escalation · line 41 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
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 | $0.00036 | $0.01284 |
| Opus 5.5 | $0.00014 | $0.00514 |
| Sonnet 5.5 | $0.00007 | $0.00257 |
| Haiku 4.5 | $0.00004 | $0.00128 |
Grade A, and why
workflow-tournament 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 1mo 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 — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Execute a tournament-style parallel implementation: $ARGUMENTS
Purpose
You are executing a parallelized "tournament" implementation workflow. Instead of decomposing a feature into smaller tasks for individual agents, you will create multiple isolated Git worktrees. You will dispatch one sub-agent to each worktree to build the entire feature independently. Once all sub-agents finish, you will review their implementations, select the best one along with the user, and merge it back into the primary feature branch.
This approach maximizes exploration of different implementation strategies and keeps the canonical codebase cleanly isolated until a winner is chosen.
Pre-Conditions
Before starting, verify:
- You are on a tracked feature branch (e.g.,
feat/Xorfix/Y). - The working directory is clean (
git status). - You know how many parallel worktrees to create (default to 5 if not specified in $ARGUMENTS, max 10).
Process
Step 1: Setup Parallel Worktrees
For each of the N sub-agents (e.g., from 1 to N):
- Create a unique branch for the sub-agent based on the current feature branch:
git branch <current-branch>-agent-<N> - Add a Git worktree inside a
.worktrees/directory (ensure.worktreesis in.gitignore):mkdir -p .worktrees git worktree add .worktrees/agent-<N> <current-branch>-agent-<N> - Initialize the workspace: Navigate into the worktree and install dependencies:
cd .worktrees/agent-<N> pnpm install # Copy any necessary environment files (e.g., cp ../../.env ./)
Step 2: Dispatch Sub-Agents
Dispatch a sub-agent to each initialized worktree concurrently.
For each sub-agent:
- Provide context: Give them the complete specification/ADR for the feature they need to build.
- Set the working directory: Ensure the sub-agent operates strictly within its assigned worktree (
.worktrees/agent-<N>). - Set the objective: Instruct the sub-agent to implement the entire feature, ensuring all tests pass within their worktree.
- Define output: Require a structured summary of their implementation approach, trade-offs made, and test results.
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.
- 1mo ago First seen · 120 lines · 36 tokens per session scan A 2e1defce3e8b
workflow-tournament is a skill published in the GitHub repository Kastalien-Research/thoughtbox (65 stars, last pushed 3mo ago), licensed MIT. It adds 36 tokens to every session and 1,284 once invoked, about $0.0001 per session on Opus 5.5. 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
datalad
Retrieves, versions, and publishes scientific datasets with DataLad and git-annex, and captures computational provenance with datalad run, rerun, and containers-run. Use when cloning or fetching data from OpenNeuro, DANDI, datasets.datalad.org, or any DataLad dataset; when a file in a dataset reads as a broken symlink…
commit-context
Trace a file, function, or line back to the agent session that produced its current commit. Use when the user asks "why is this code here", "what was the agent doing when this changed", "who wrote this", or wants context on a specific location in the codebase.
commit-history
List recent git commits linked to agent sessions, optionally filtered by branch or repo. Use when the user asks "show agent commits", "what has the agent shipped", "list linked commits", or wants commits with their session context.
baby-sit
Monitor a GitHub pull request until CI is green, diagnose failures, and rerun only evidence-backed flaky GitHub Actions jobs.
cyrus-setup-repository
Add one or more Git repositories to Cyrus configuration so it can process issues from those repos.
github-commenting
How to post clean, rich, deduplicated GitHub PR review comments — suggestion blocks, multi-line anchors, markers, formatting rules. Load before posting or fixing any PR comment.