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 instructions/rjmurillo/ai-agents/pragmatic-programmergit clone --depth 1 https://github.com/rjmurillo/ai-agentsWrote 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/instructions/rjmurillo/ai-agents/pragmatic-programmer)<a href="https://agentmods.dev/instructions/rjmurillo/ai-agents/pragmatic-programmer"><img src="https://agentmods.dev/badge/instructions/rjmurillo/ai-agents/pragmatic-programmer.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 | $0.02246 | $0.02246 |
| Opus 5 | $0.01123 | $0.01123 |
| Sonnet 5 | $0.00449 | $0.00449 |
| Haiku 4.5 | $0.00225 | $0.00225 |
Grade A, and why
ai-agents pragmatic-programmer.instructions.md 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.
How it starts
The opening of the file, as written. The whole thing — 299 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The Pragmatic Programmer
Purpose
This repository follows The Pragmatic Programmer in the sense of Andrew Hunt and David Thomas: work pragmatically, take responsibility for quality, automate what is repetitive, and keep code and process adaptable.
All code generation, edits, and reviews must optimize for:
- clear ownership and responsibility
- DRY at the knowledge level
- orthogonality
- incremental delivery
- ruthless feedback
- automation of repetitive work
- code that is easy to change and easy to reason about
This file is a binding engineering policy for Claude.
For deeper design decisions, apply the same engineering qualities directly: maximize cohesion, minimize coupling, preserve encapsulation, prioritize testability, and avoid redundant knowledge.
Primary Directive
Be pragmatic, not dogmatic.
When uncertain, choose the option that:
- reduces knowledge duplication
- keeps concerns independent
- shortens feedback loops
- automates what is repeated
- leaves the system easier to change
- makes intent clearer to future maintainers
Do not follow style or process rituals that do not improve outcomes.
Core Pragmatic Principles
Own the Result
- Take responsibility for the quality and changeability of the code you touch.
- Do not blame tooling, framework defaults, or "existing style" for avoidable bad design.
- Surface trade-offs, risks, and uncertainty explicitly.
Think Beyond the Local Edit
- Every change affects future maintainability.
- Small quick fixes that multiply future cost are usually a bad bargain.
- Leave the area better than you found it.
Favor Adaptability
- Build systems that are easy to observe, test, and change.
- Prefer flexible boundaries over brittle cleverness.
- Avoid premature commitment when requirements are still moving.
DRY Rules
DRY means do not duplicate knowledge, not merely do not duplicate text.
- A business rule should have one authoritative representation.
- Validation logic for the same concept should not be scattered.
- Status semantics, mappings, and calculations should not be copied across layers.
- Configuration and schema meaning should not be repeated inconsistently.
- Avoid duplicated process steps that can be automated.
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.
- yesterday First seen · 299 lines · 2,246 tokens per session scan A 6849291bf0c5
ai-agents pragmatic-programmer.instructions.md is an instructions file published in the GitHub repository rjmurillo/ai-agents (45 stars, last pushed yesterday), licensed MIT. It adds 2,246 tokens to every session, about $0.0112 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 instructions, from other repositories
abtars AGENTS.md
Instructions for aksika/abtars, covering agents.md, quick commands, architecture, model-call chokepoint: spin(spec) (#1271) and external dependency: abmind.
Alex_Skill_Mall falsifiability-deadlines.instructions.md
Every new or edited brain artefact (instruction / skill / prompt / agent) must declare a specific falsification deadline — a literal date, an observable event, or count+time bound — not 'after N passes' or 'when conditions warrant'.
norma CLAUDE.md
Instructions for yanlingLabs/norma, covering claude.md, what this is, commands, tests and swift.
Alex_Skill_Mall mall-maintenance-rules.instructions.md
Always-on routing for Mall maintenance work — fires the right Mall skill at the right moment. Distinguishes Mall-owned automation from out-of-scope editorial work.
Alex_Skill_Mall lint-discipline.instructions.md
Fix lint always — if I edited a file, I own its lint state on exit, even for pre-existing findings.
bed-of-roses CLAUDE.md
Instructions for SixHq/bed-of-roses, covering claude.md, project, commands, architecture and server/ — node runtime (the brain).