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 skills/spumer/i-m-senior-developer/fpf-integrationnpx skills add spumer/i-m-senior-developer --skill fpf-integrationgit clone --depth 1 https://github.com/spumer/i-m-senior-developerWrote 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/spumer/i-m-senior-developer/fpf-integration)<a href="https://agentmods.dev/skills/spumer/i-m-senior-developer/fpf-integration"><img src="https://agentmods.dev/badge/skills/spumer/i-m-senior-developer/fpf-integration.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 | $0.00116 | $0.04313 |
| Opus 5 | $0.00058 | $0.02157 |
| Sonnet 5 | $0.00023 | $0.00863 |
| Haiku 4.5 | $0.00012 | $0.00431 |
Grade A, and why
fpf-integration 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 4d 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 — 303 lines — stays where its author put it; the contents beside it link to each section on GitHub.
FPF Integration for Multi-Agent Systems
Integrate First Principles Framework (FPF) into multi-agent projects to improve decision quality, reduce cognitive biases, and ensure evidence-based reasoning.
Источник: First Principles Framework (FPF) —
https://github.com/ailev/FPF(FPF-Spec). Этот скилл — практическая обвязка для интеграции FPF в проекты; канонические определения аксиом (A.7, A.10, A.11, A.1.1, NQD, DRR и др.) живут в FPF-Spec. См. протокол доступа к спецификации ниже.
Доступ к спецификации ОБЯЗАТЕЛЕН. Работа скилла требует доступа к каноническому тексту FPF — одним из двух источников, по приоритету: сначала FPF-справочник через MCP (если подключён — самый авторитетный: точные ID, цитаты, живая свежесть), иначе локальная копия
FPF-Spec.md(~9.5 МБ, не входит в плагин). Нет ни того, ни другого — скилл не переходит в «облегчённый» режим и не работает по памяти: он блокируется и требует настроить доступ (см. «Протокол доступа к FPF» → Уровень 3). Проверка источника — в момент первого обращения к спеке, не при активации.
Entry Point Decision Tree
- New project, no artifacts → Phase 0 + Phase 1a (Foundation)
- Existing project, need full integration → Phase 0 + Phase 1b (Audit) + Phase 2-5
- Single decision review → Phase 1b step 2 only (6-question express review)
- Add checklists to roles → Phase 2 only
- Upgrade decision format → Phase 3 only
Core FPF Principles (Quick Reference)
| Principle | Rule | Check |
|---|---|---|
| A.10 Evidence Graph | Claim without proof = opinion | "Source? Method? Date?" |
| A.7 Strict Distinction | Description != capability != fact | "Is this how it SHOULD work or how it DOES work?" |
| A.1.1 BoundedContext | Meaning is local, translation explicit | "Does this term mean the same thing to all roles?" |
| A.11 Parsimony | Add only what cannot be subtracted | "Can existing tools express this?" |
| NQD | >= 3 alternatives before choosing | "What are 2 more options?" |
| DRR Decay | Evidence expires, decisions need review dates | "When does this evidence go stale?" |
What ships with it
9 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.
- CHANGES-fpf-spec.md 11 KB
- references/audit-patterns.md 8.3 KB
- references/fpf-glossary.md 19 KB
- references/fpf-grep-patterns.md 7.1 KB
- references/fpf-sections-map.md 85 KB
- references/fpf-tasks-lookup.md 5.9 KB
- references/practical-tools.md 4.8 KB
- references/role-templates.md 9.9 KB
- scripts/fetch-fpf-spec.sh 2.8 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.
- 4d ago First seen · 303 lines · 116 tokens per session scan A 7b8830c63af4
fpf-integration is a skill published in the GitHub repository spumer/i-m-senior-developer (11 stars, last pushed 2d ago), licensed MIT. It adds 116 tokens to every session and 4,313 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…