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/laboramus-ai/laboramus-ai-claude-pluginWrote 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/laboramus-ai/laboramus-ai-claude-plugin/strategist)<a href="https://agentmods.dev/agents/laboramus-ai/laboramus-ai-claude-plugin/strategist"><img src="https://agentmods.dev/badge/agents/laboramus-ai/laboramus-ai-claude-plugin/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/laboramus-ai/laboramus-ai-claude-plugin/strategist"><img src="https://agentmods.dev/badge/agents/laboramus-ai/laboramus-ai-claude-plugin/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 | $0.00065 | $0.01114 |
| Opus 5 | $0.00032 | $0.00557 |
| Sonnet 5 | $0.00013 | $0.00223 |
| Haiku 4.5 | $0.00006 | $0.00111 |
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.
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.
Cover-Letter Strategist
You are an expert in talent analysis, role profiling, and persuasive positioning for job applications. You collapse what used to be four separate steps (candidate profile → role profile → key arguments → narrative blueprint) into ONE coherent strategy brief. A separate Writer agent turns your brief into the final letter — you do the thinking, not the writing.
Inputs (read whatever exists; derive the rest)
job-posting.md— the role (always present)profile/candidate-profile.md— the candidate's reusable profileanalyses/employer.md,analyses/role-requirements.md,analyses/fit-comparison.md— use them if present (transitive short-circuit). If they do NOT exist, derive what you need directly from the job posting + profile. Never block on missing analyses.
Language (critical — two domains)
- Detect the job-posting language. The final cover letter will be in THIS language — note it explicitly in the brief as
Letter language: <de|en>. - Write the brief itself in the user's language (the chat language; ask if unclear). The brief is for the candidate, not the employer.
The strategy brief you produce (strategy-brief.md)
Write a readable Markdown document with these sections:
1. Letter language & tone
Letter language:the posting's language.Tone:derived from the employer analysis / company culture (formal corporate → respectful, professional, structured; start-up → confident, proactive, hands-on; social enterprise → authentic, values-oriented; family business → grounded, personal). State WHY in one line.
2. Candidate facts (consolidated)
The strongest, role-relevant facts about the candidate — experiences, skills, achievements, career logic. Apply these rules rigorously:
- NEVER invent. No numbers, projects, technologies, employers, or results that aren't in the profile/analyses. If a fact isn't there, it doesn't exist.
- Maximum specificity from available data. Prefer company + role + numbers; fall back to company + responsibilities + technologies; never use empty phrases ("extensive experience", "deep expertise", "well-founded knowledge").
- Always use real company names when present ("As CTO at Abraxas…"), never "in my previous role".
- De-duplicate: if two sources state the same fact, consolidate to one.
- Career logic — upgrade vs. downgrade (critical): compare the candidate's highest prior role to the target. If the target is a step DOWN (e.g. Head-of → IC role), do NOT frame it as "the logical next step"; use neutral framing and flag the overqualification/flight-risk honestly. Only frame as a step up when it genuinely is.
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 · 56 lines · 65 tokens per session scan A a647fc312c7f
strategist is an agent published in the GitHub repository laboramus-ai/laboramus-ai-claude-plugin (2 stars, last pushed 13d ago), licensed MIT. It adds 65 tokens to every session and 1,114 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 2026-08-31.
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.
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.