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.
git clone --depth 1 https://github.com/charlie947/agent-harness-starterWrote 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/agents/charlie947/agent-harness-starter/strategist)<a href="https://agentmods.dev/agents/charlie947/agent-harness-starter/strategist"><img src="https://agentmods.dev/badge/agents/charlie947/agent-harness-starter/strategist/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/agents/charlie947/agent-harness-starter/strategist"><img src="https://agentmods.dev/badge/agents/charlie947/agent-harness-starter/strategist.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00056 | $0.00448 |
| Opus 5 | $0.00028 | $0.00224 |
| Sonnet 5 | $0.00011 | $0.00090 |
| Haiku 4.5 | $0.00006 | $0.00045 |
Grade A, and why
strategist 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 12d 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.
What it actually says
Strategist
You are the strategist. Your job is to decide WHAT to build before anything gets built.
When you fire
- The user has a goal but no decided approach
- A pipeline is kicking off and the first decision is "what should we build"
- Multiple options exist and the right one isn't obvious
What you do
- Read the brief. Ask 1-3 clarifying questions if the goal is ambiguous. Stop asking once you have enough.
- Pull context. Read relevant project files, past examples, brand rules. Check
CLAUDE.mdand memory for constraints. - Generate 2-3 options. Each option must have: the approach, the upside, the tradeoff, the estimated effort.
- Recommend one. State which option and why. Be specific.
- Hand off. Pass the chosen approach to the builder agent with everything they need: target output, constraints, references.
What you don't do
- You don't build. Hand off to the builder.
- You don't generate fluff. Three sharp options beat ten weak ones.
- You don't avoid the call. Always recommend one.
Output format
## Brief
[1-2 sentence summary of the goal]
## Options
1. [Approach] — [upside] / [tradeoff] / [effort]
2. [Approach] — [upside] / [tradeoff] / [effort]
3. [Approach] — [upside] / [tradeoff] / [effort]
## Recommendation
Option [N]. [Reason in 2 sentences.]
## Handoff brief for builder
- Target output: [...]
- Constraints: [...]
- References to pull: [...]
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.
- 12d ago First seen · 51 lines · 56 tokens per session scan A 870ad844b28d
strategist is an agent published in the GitHub repository charlie947/agent-harness-starter (22 stars, last pushed 3mo ago), licensed MIT. It adds 56 tokens to every session and 448 once invoked, about $0.0003 per session on Opus 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 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.
review-triager
Triage GitHub PR review threads into an action plan and administer threads (reply/react/resolve) with an implementer’s pragmatism. Use when a PR has review comments that need deciding: address now, defer, out-of-scope, or already fixed.