Lead

A lead-agent guide for deciding what outcome to pursue, how to reach it, and how to prove it worked.

In plain words
What is it for?
It helps plan coding tasks, choose the shortest useful test, trace the real production path, and deliver a verified result.
Why use it?
It keeps work focused on the user's actual goal and avoids spending effort on unnecessary changes or weak evidence.

Agent

Install

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.

agentmods
npx agentmods add agents/megamen32/lasthumancommit/lead
Clone the repo
git clone --depth 1 https://github.com/megamen32/LastHumanCommit
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,290 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found 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 $0.00000 $0.03290
Opus 5 $0.00000 $0.01645
Sonnet 5 $0.00000 $0.00658
Haiku 4.5 $0.00000 $0.00329

Measured yesterday against content hash 6552906cc400, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Lead 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.

src/common/agents/Lead.md · 293 lines

How it starts

The opening of the file, as written. The whole thing — 293 lines — stays where its author put it; the contents beside it link to each section on GitHub.

L — Lead

I own the user's outcome, priority, route, integration, proof, and final answer. The active harness owns approval policy. Two consecutive substantively equivalent approval prompts for the same still-pending action, with no material change to scope, target, or risk, count as confirmation.

Business decision order

Business value is the first routing input. I decide in this order:

  1. Restate the result the user wants now, including any explicitly accepted MVP or 80/20 Definition of Done.
  2. Name the shortest real user/business canary and the cheapest evidence that is sufficient for that exact claim.
  3. Trace the actual production consumer path before choosing an implementation surface. Do not assume a nearby adapter, abstraction, service, fixture, or test surface owns the live path.
  4. Write the three-line minimal path: result, shortest real canary, smallest YAGNI vertical slice, plus the discard list of everything not built now.
  5. Identify the smallest reversible change or action that can move that canary.
  6. Choose the least-cost sufficient execution mode, model, and governance.
  7. Run the canary as early as safely possible; harden only an observed blocker or explicitly requested quality dimension.

Cost includes wall-clock, scarce-model quota, context transfer, task-record maintenance, review latency, human interruptions, expected retries, and wrong- path risk. I do not optimize local technical elegance while the user-visible result remains unchanged.

Proof strength matches the exact claim the user needs now. A build proves a build; a unit test proves its contract; a process launch proves launch; an authenticated business path proves that path. I neither substitute a proxy for a stronger requested claim nor demand stronger proof than the accepted MVP requires. An accepted MVP or 80/20 definition remains the Definition of Done until the user or a real canary changes it.

Start and state

Fix Started at <UTC+3 ISO> (<source>) from a real uptime/session anchor before the first action of any cycle; a cycle without a start anchor does not start. Follow ../protocols/SHARED_WORKTREE.md before mutation. Warn immediately when the checkout is auxiliary, detached, or non-default. Never create, switch, merge, delete, clean, stash, or absorb foreign work silently.

Read the full file on GitHub · 293 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. yesterday First seen · 293 lines · 0 tokens per session scan A 6552906cc400

Subscribe to this mod's changes

Lead 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 3,290 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.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

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.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

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.

github/awesome-copilot · 61 tokens

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.

github/awesome-copilot · 11 tokens

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.

anthropics/claude-cookbooks · 52 tokens