strategist

strategist is an agent for Claude Code from laboramus-ai/laboramus-ai-claude-plugin. It costs 65 tokens per session (1,114 once invoked), scanned A, original, MIT.

An agent that turns a job posting, candidate profile, and available analyses into one cover-letter strategy brief. The brief explains how the candidate should present their experience before another agent writes the letter.

In plain words
What is it for?
Use it to identify role requirements, compare them with a candidate’s experience, choose the strongest arguments, plan the letter’s story, and record the letter language.
Why use it?
It separates the reasoning from the final writing, so you can review and correct the proposed positioning before a cover letter is produced.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the laboramus-ai plugin — 11 skills, 2 agents shipped together

Good fit Use it to identify role requirements, compare them with a candidate’s experience, choose the strongest arguments, plan the letter’s story, and record the letter language.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/laboramus-ai/laboramus-ai-claude-plugin/strategist
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.

Clone the repo
git clone --depth 1 https://github.com/laboramus-ai/laboramus-ai-claude-plugin

Made for: Claude Code.

Or install laboramus-ai, the plugin that ships this one along with the rest of its 11 skills, 2 agents.

Wrote 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.

agentmods badge for strategist

README.md
[![agentmods](https://agentmods.dev/badge/agents/laboramus-ai/laboramus-ai-claude-plugin/strategist/github.svg)](https://agentmods.dev/agents/laboramus-ai/laboramus-ai-claude-plugin/strategist)
Your own site
<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.

agentmods 80×15 button for strategist

Your own site · 80×15
<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>
Per session 65 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,114 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00065 $0.01114
Opus 5 $0.00032 $0.00557
Sonnet 5 $0.00013 $0.00223
Haiku 4.5 $0.00006 $0.00111

Measured 12d ago against content hash a647fc312c7f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

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.

agents/strategist.md · 56 lines

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 profile
  • analyses/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.

Read the full file on GitHub · 56 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. 12d ago First seen · 56 lines · 65 tokens per session scan A a647fc312c7f

Subscribe to this mod's changes

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.

Related

Other agents, from other repositories