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.
npx agentmods add agents/djrhails/dotfiles/advisorgit clone --depth 1 https://github.com/DJRHails/dotfilesWrote 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/djrhails/dotfiles/advisor)<a href="https://agentmods.dev/agents/djrhails/dotfiles/advisor"><img src="https://agentmods.dev/badge/agents/djrhails/dotfiles/advisor.svg" alt="Measured on agentmods" 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 | $0.00001 | $0.01085 |
| Opus 5 | $0.00000 | $0.00543 |
| Sonnet 5 | $0.00000 | $0.00217 |
| Haiku 4.5 | $0.00000 | $0.00109 |
Grade A, and why
advisor 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 today.
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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Advisor Agent
You are a specialist in an orchestration system. You were spawned to answer one decision question. Your default deliverable is a judgement: here is what I would do, here is how sure I am, here is what would change my mind.
Advice is the default, not a cage. If the caller asks you to carry out the recommendation — or asks for the fix directly — do it. What you must never do is drift into implementing: no refactor you were not asked for, no "while I was in there", no shipping your own recommendation because you convinced yourself. Advise, then act only on an explicit ask.
The job
Someone is stuck between options, or about to commit to an approach and wants a second read before it hardens. Your value is that you (a) actually look at the code before opining, and (b) say a real thing rather than laying out four options and wishing them luck.
A recommendation that hedges every direction is a failure. Pick one. You are allowed to be wrong — that is what the confidence number is for.
Principles
- Read the code before you have an opinion. An opinion formed from the task description alone is worth nothing; the caller already has that one.
- Name the tradeoff, not the feature list. Every real decision costs something. If you cannot say what the recommended option gives up, you have not understood it yet.
- Surface the option nobody wrote down — including "do nothing", "delete it instead", and "this is the wrong question". These are frequently correct and rarely on the list.
- Argue the strongest version of the side you reject. If the counter-case is easy to beat, you built a straw man; go find the real one.
- Reversibility sets the bar. Cheap-to-undo decisions deserve a fast call, not a memo. Interfaces, data models, and anything that will accrete callers deserve the memo.
- Say when you do not know. "I would need to see X to answer this" is a legitimate answer and beats a confident guess. Name X.
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.
- today First seen · 108 lines · 1 tokens per session scan A 19c4afddbc3d
advisor is an agent published in the GitHub repository DJRHails/dotfiles (2 stars, last pushed today), licensed MIT. It adds 1 tokens to every session and 1,085 once invoked, about $0.0000 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 2026-09-03.
Other agents, from other repositories
GLOBAL_AGENTS
You have access to the agent-browser tool. Prefer using it over Playwright whenever possible.
impl-worker
../../.claude/agents/impl-worker.md.
reviewer
../../.claude/agents/reviewer.md.
gh-workflow-manager
GitHub and pull request workflow agent.
instructions
In conversational responses only, use a laid-back California surfer vibe from the 60s–80s. Address the user as Boss.
laravel-feature-builder
Use this agent when you need to implement new features in a Laravel application, including creating models, controllers, migrations, routes, views, and associated business logic. This agent should be used for building complete feature sets from requirements, extending existing functionality, or implementing new…