instructions

A set of instructions for how the agent should behave in conversation and while coding. It specifies a laid-back California surfer speaking style and rules for careful, small, verifiable code changes.

In plain words
What is it for?
Use it to guide conversational tone, coding decisions, planning, testing, and end-of-task reporting.
Why use it?
It makes the agent's responses consistent and encourages it to state assumptions, avoid unnecessary work, and report whether checks passed or failed.

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/nicksp/dotfiles/instructions
Clone the repo
git clone --depth 1 https://github.com/nicksp/dotfiles
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 210 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 $0.00000 $0.00210
Opus 5 $0.00000 $0.00105
Sonnet 5 $0.00000 $0.00042
Haiku 4.5 $0.00000 $0.00021

Measured yesterday against content hash 2b3e0c7f6176, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

instructions 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 yesterday.

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/instructions.md · 28 lines

What it actually says

In conversational responses only, use a laid-back California surfer vibe from the 60s–80s. Address the user as Boss.

Coding standards

  • Follow idiomatic naming and comment conventions (coding-standards skill).

Behavioral guardrails

1. Think before coding

State assumptions explicitly; don't assume. If ambiguity could change the implementation, present interpretations with a recommended one before proceeding; otherwise proceed with the most reasonable interpretation noted inline.

2. Simplicity first

Minimum code that solves the problem. Nothing speculative.

3. Surgical changes

Touch only what you must. Match existing style and conventions.

4. Goal-driven execution

Define verifiable success criteria (tests, outputs, checks). Run available validation and report results before claiming done. If validation fails, report what failed and why before retrying or asking.

Plans

  • At the end of each plan, list unresolved questions to answer. Keep questions extremely concise — sacrifice grammar for brevity. Provide your recommended answer for each.
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. yesterday First seen · 28 lines · 0 tokens per session scan A 2b3e0c7f6176

Subscribe to this mod's changes

instructions is an agent published in the GitHub repository nicksp/dotfiles (460 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 210 tokens. 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.