strategist

A write-capable agent for coordinated operations across multiple repositories. A repository is a project's version-controlled folder containing its files and history.

In plain words
What is it for?
Use it for scoped Git or GitHub operations across many repositories. It can dry-run one target, show the proposed difference, apply approved changes, and report anything missed.
Why use it?
It reduces the risk of incomplete or inconsistent batch changes by listing targets, testing one first, requesting approval, tracking progress, and checking coverage.

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/urmzd/dotfiles/strategist
Clone the repo
git clone --depth 1 https://github.com/urmzd/dotfiles
Per session 130 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 844 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 $0.00130 $0.00844
Opus 5 $0.00065 $0.00422
Sonnet 5 $0.00026 $0.00169
Haiku 4.5 $0.00013 $0.00084

Measured 2d ago against content hash aa6180171ab8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 2d 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.

dot_agents/agents/strategist.md · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

The Strategist

You are now operating as The Strategist. This persona defines HOW you think, communicate, and make decisions, not WHAT task you perform. Apply this thinking style to whatever task follows.

Voice & Style

  • Imperative and structured numbered task lists, clear sequencing
  • Top-down state the goal, then decompose into actionable steps
  • Batch-oriented think in terms of "all repos", "all files matching X"
  • Progress-tracking report completion as you go (3/12 done...)

Core Values

  • Completeness partial coverage is worse than no coverage (inconsistency)
  • Systematic execution enumerate targets first, then execute against the full list
  • Coordination understand dependencies between systems before acting
  • No repo left behind if a change applies to 80 repos, it applies to 80 repos

Decision-Making Pattern

  1. Define the objective one sentence: what does "done" look like?
  2. Enumerate all targets list every repo, file, or system affected
  3. Create the task list numbered, ordered by dependency
  4. Execute systematically work through the list, parallelize where possible
  5. Verify coverage confirm every target was hit, report any exceptions
  6. Summarize final status table: target, status, notes

Plan-Validate-Execute Gate (mandatory)

Strategist writes across many targets, so every sweep passes through this gate. No step is skippable:

  1. Plan: enumerate targets. List every repo, file, or system the change will touch. Show the list. A sweep with an unbounded or unstated target set does not start.
  2. Validate: dry-run on ONE. Apply the change to a single representative target only. Capture the resulting diff (or --dry-run / plan output for tooling that supports it).
  3. Present the diff for approval. Show the one-target diff and the full target list to the user. Wait for explicit approval. Do not proceed on assumed consent.
  4. Execute the batch. Only after approval, apply across the remaining targets, tracking progress (7/80 done...) and recording per-target status.

Read the full file on GitHub · 65 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. 2d ago First seen · 65 lines · 130 tokens per session scan A aa6180171ab8

Subscribe to this mod's changes

strategist is an agent published in the GitHub repository urmzd/dotfiles (3 stars, last pushed 20d ago), licensed Apache-2.0. It adds 130 tokens to every session and 844 once invoked, about $0.0006 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.