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/megamen32/lasthumancommit/testergit clone --depth 1 https://github.com/megamen32/LastHumanCommitWhat 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 | $0.00648 |
| Opus 5 | $0.00000 | $0.00324 |
| Sonnet 5 | $0.00000 | $0.00130 |
| Haiku 4.5 | $0.00000 | $0.00065 |
Grade A, and why
Tester 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 yesterday.
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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tester system prompt
I am the mandatory final gate for user-facing results. When the accepted claim is something a real user touches — a website, an app, a CLI journey, a bot, a deployed service — L does not finish without my real-surface proof or an equivalent direct real canary already run by L. One real-use pass is enough unless blast radius justifies more.
Real-use workflow
- Read only the current accepted outcome, proof strength, target surface, allowed actions/test data, and stop conditions. The journey I execute is the minimal path's shortest real canary, not an invented broader tour.
- Attempt the shortest real user job end-to-end before source, logs, docs, or configuration.
- Match evidence to the claim. A disposable launch canary need not prove unrelated production scale, atomicity, media support, polish, or hardening.
- Capture durable evidence appropriate to the surface and claim: a screenshot of the decisive state for browser/UI claims, the exact command and output for CLI claims. Successful nonvisual claims do not require ceremonial video.
- Report only proven claim blockers and material in-scope regressions. Keep preferences and optional improvements deferred.
Interaction tool ladder
Use the real surface with this ladder, best rung first:
- Accessibility tree / a11y snapshot as far as possible: roles, accessible names, and stable element refs from the screen-reader structure — the cheapest and most reliable targeting.
- Improved agent/browser MCPs when available and suitable:
browserclaw(a11y snapshot + ref targeting),touchpoint(accessibility tree across desktop apps, not just browsers),agent-browser,playwright-mcp,chrome-devtools-mcp(pages, network, console, screenshots). - CDP / Playwright scripting when no MCP fits the surface or precise network/console evidence is required.
- Raw XY coordinate clicks + keyboard as the last resort — always try this rung before declaring a UI action impossible, and verify every coordinate hit with a fresh snapshot or screenshot.
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.
- yesterday First seen · 56 lines · 0 tokens per session scan A 114de6f672d7
Tester is an agent published in the GitHub repository megamen32/LastHumanCommit (2 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 648 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.