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 skills add racastellanosm/agent-skills --skill qrspi-methodologygit clone --depth 1 https://github.com/racastellanosm/agent-skillsWrote 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/skills/racastellanosm/agent-skills/qrspi-methodology)<a href="https://agentmods.dev/skills/racastellanosm/agent-skills/qrspi-methodology"><img src="https://agentmods.dev/badge/skills/racastellanosm/agent-skills/qrspi-methodology/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.
<a href="https://agentmods.dev/skills/racastellanosm/agent-skills/qrspi-methodology"><img src="https://agentmods.dev/badge/skills/racastellanosm/agent-skills/qrspi-methodology.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00065 | $0.04226 |
| Opus 5 | $0.00032 | $0.02113 |
| Sonnet 5 | $0.00013 | $0.00845 |
| Haiku 4.5 | $0.00006 | $0.00423 |
Grade A, and why
qrspi-methodology 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.
How it starts
The opening of the file, as written. The whole thing — 265 lines — stays where its author put it; the contents beside it link to each section on GitHub.
QRSPI Methodology: Engineering Workflow Guide
The QRSPI methodology is an agentic engineering protocol designed to guarantee deterministic, high-quality, and regression-free software outcomes across 5 sequential phases:
[ 1. QUESTION ] ➔ [ 2. RESEARCH ] ➔ [ 3. STRUCTURE ] ➔ [ 4. PLAN ] ➔ [ 5. IMPLEMENT ]
🛡️ Core Engineering Invariants & Principles
AI agents must strictly adhere to three non-negotiable engineering principles across all phases to eliminate silent assumptions, code bloat, and accidental regressions:
[!IMPORTANT]
1. Think Before Coding (Don't Guess. Surface Confusion. Present Trade-Offs.)
- State Assumptions Explicitly: Never pick an interpretation silently and run with it. If uncertain, state the assumption clearly or ask.
- Surface Ambiguity & Stop on Confusion: If requirements or codebase ground truths conflict, stop immediately and name what is unclear.
- Push Back When Warranted: If a simpler, more idiomatic, or standard alternative exists, actively propose it rather than blindly implementing an overcomplicated request.
- Present Trade-Offs: Outline concrete pros and cons when design decisions exist instead of choosing quietly.
[!IMPORTANT]
2. Simplicity First (Minimum Code. Zero Speculative Engineering.)
- Occam's Engineering: Write the minimum code that cleanly solves the problem. Nothing speculative.
- No Premature Abstractions: Never introduce interfaces, design patterns (Factory, Strategy, etc.), or layers for single-use code.
- No Unrequested Flexibility: Build exactly what is requested—avoid speculative "configurability" or over-defensive error handling for impossible scenarios.
- The Senior Engineer Simplicity Test: "If 200 lines could be 50, rewrite it." Always choose the direct, maintainable solution.
[!IMPORTANT]
3. Surgical Changes (Touch Only What You Must. Zero Orthogonal Edits.)
- Blast Radius Containment: Touch ONLY the files and symbols strictly required to fulfill the task.
- Zero Orthogonal Refactoring: Do NOT "improve", reformat, or re-indent adjacent functions, files, or comments that aren't broken.
- Preserve Comments & Existing Style: Never delete, mutate, or strip existing comments/docstrings. Strictly match the style and idioms of the surrounding codebase.
- Unrelated Dead Code Policy: If you encounter unrelated dead code or tech debt, mention it in the execution summary—NEVER delete or edit it silently.
What ships with it
10 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- hooks/prompt-hook.sh 5.3 KB runs code
- README.md 6.2 KB
- references/index-template.md 1.1 KB
- references/phases-checklist.md 3.5 KB
- references/stage-templates/1-question.md 4.2 KB
- references/stage-templates/2-research.md 1.3 KB
- references/stage-templates/3-structure.md 2.1 KB
- references/stage-templates/4-plan.md 2.2 KB
- references/stage-templates/5-implement.md 1.8 KB
- scripts/verify-session.sh 1.8 KB runs code
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.
- 12d ago First seen · 265 lines · 65 tokens per session scan A 0924b8646706
qrspi-methodology is a skill published in the GitHub repository racastellanosm/agent-skills (1 stars, last pushed 20d ago), licensed MIT. It adds 65 tokens to every session and 4,226 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.
Other skills, from other repositories
agent-orchestrator
Meta-skill que orquestra todos os agentes do ecossistema. Scan automatico de skills, match por capacidades, coordenacao de workflows multi-skill e registry management.
ask-matt
Ask which skill or flow fits your situation. A router over the user-invoked skills in this repo.
project-planning
Converts a specification into a phased, dependency-ordered implementation plan. Use after specification is complete and before execution begins.
design-first
Guides the creation of technical design documents before writing code, producing architecture diagrams, data models, API interface definitions, implementation plans, and multi-option trade-off analyses. Use when the user asks to plan a feature, architect a system, design an API, explore implementation approaches, or…
architecture-sketching
Defines types and boundaries before implementation.
refactoring-workflow
Improve the structure of existing code without changing its behaviour, in small verified steps under a green test suite. Use when the user asks to refactor, clean up, restructure or simplify code, wants to reduce duplication or coupling, is preparing a codebase for a feature it cannot currently accommodate, or when…