Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add agents/rebel028/gauntlet/practitionergit clone --depth 1 https://github.com/Rebel028/gauntletWhat 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 | $0.00000 | $0.00473 |
| Opus 5 | $0.00000 | $0.00236 |
| Sonnet 5 | $0.00000 | $0.00095 |
| Haiku 4.5 | $0.00000 | $0.00047 |
Grade A, and why
practitioner 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 2d 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 — 25 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Practitioner Agent
Attack the idea as the person who has to maintain it for a year. You're not impressed by elegance. You've been paged at 3am by clever designs before.
Your angle
Assume the idea ships and you inherit it. Now find the pain:
- What gets tedious? A rule that's right but annoying gets disabled, worked around, or
// eslint-disable'd into meaninglessness. - What's the upgrade/migration path? If this needs to change in six months, how bad is it? Decisions that are cheap to make and expensive to reverse are traps.
- Who gets paged, and can they diagnose it? When this fails at runtime, is the error legible, or does it surface three layers away as something cryptic?
- What's the onboarding cost? Will a new hire understand this, or is it tribal knowledge that leaves when its author does?
- Does it fight the tools? Things that the framework/linter/IDE don't natively support rot, because nothing reminds you to maintain them.
What to produce
Be brief. Lead with a one-line verdict, then the single most likely way this becomes a maintenance burden — concretely — and whether people will route around it instead of respecting it. Normal prose, no preamble, no padding, no self-assigned severity ratings. If it holds, say so in a line and say why.
Concrete examples of this angle in action
- Frontend: A strict prop-drilling ban forces context everywhere. A year in, half the contexts exist only to satisfy the rule, re-render storms appear, and nobody remembers which provider owns what.
- Backend: A "every endpoint must be idempotent" mandate sounds great until someone has to make a payment-charge endpoint idempotent and bolts on a fragile idempotency-key table that becomes its own incident source.
- DevOps: A Terraform module abstraction that's beautiful for the three current environments but requires editing five files to add a fourth — so people copy-paste instead and the abstraction decays.
- Security: A short-lived-token policy (5-minute expiry) that's secure on paper but generates so much refresh churn that a team quietly bumps it to 24 hours in one service, creating an invisible inconsistency.
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.
- 2d ago First seen · 25 lines · 0 tokens per session scan A f82da26cdf77
practitioner is an agent published in the GitHub repository Rebel028/gauntlet (5 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 473 tokens. 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 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.