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/dpf-authoringnpx skills add spumer/i-m-senior-developer --skill dpf-authoringgit 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/dpf-authoring)<a href="https://agentmods.dev/skills/spumer/i-m-senior-developer/dpf-authoring"><img src="https://agentmods.dev/badge/skills/spumer/i-m-senior-developer/dpf-authoring.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 | $0.00175 | $0.02780 |
| Opus 5 | $0.00088 | $0.01390 |
| Sonnet 5 | $0.00035 | $0.00556 |
| Haiku 4.5 | $0.00017 | $0.00278 |
Grade A, and why
dpf-authoring 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 5d 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DPF-Authoring — авторинг сводов принципов (DPF) по FPF
Плагин самодостаточен: скилл содержит метод, шаблоны и пакеты ролей, а нативный workflow плагина запускает конвейер. Для работы не нужен никакой конкретный проект и никакие конкретные пути машины — DPF пишутся в тот проект, который явно указан в args.repoRoot; каталог самого скилла передаётся конвейеру явным args.skillDir.
Состав скилла:
references/method.md— канон метода (6 фаз, гейты, канонический скелет, паттерны, типовые ошибки). Прочитать перед любым режимом ниже.references/lifecycle.md— задача-ориентированный маршрут поверх канона: создать/дополнить DPF, создать/обновить LPF, петля worked-evidence, гейт банка. Для того, кто хочет «с чего начать» под конкретную задачу, а не читать метод целиком.../../workflows/dpf-authoring-pipeline.js— нативный workflow плагина: конвейер из 6 фаз с передачей результатов через файлы.assets/template-dpf.md— скелет нового DPF;assets/template-source-pack.md— образец реестра происхождения.frameworks/DPF-ADVERSARIAL-REVIEW/,frameworks/DPF-KNOWLEDGE-CURATION/— встроенные пакеты ролей конвейера (формат dpf-apply:DPF.md+assets/apply-prompt.md).
Привязка к редакции: FPF ailev/FPF@f7c7e93f (E.4.DPF spine, CC-DPF.1–9, E.4.DPF.DA) — см. fpf_edition во frontmatter references/method.md. Агенты фаз читают FPF по приоритету источника: сначала FPF-справочник через MCP (fpf_reference: search_fpf / read_fpf_doc / query_fpf_spec), если он подключён — точные ID и цитаты; иначе локальная копия ~/.claude/knowledge/fpf/FPF-Spec.md. Метод запинен на редакцию выше — если MCP отдаёт другую (get_fpf_index_status), агент фазы обязан явно отметить расхождение в references/, а не работать молча по чужой редакции (edition-пин E.4.DPF.DA). Нет ни MCP, ни локальной копии — фаза не авторит по памяти, а падает громко (FAIL-FAST, A.10): нужен хотя бы один источник FPF. Свежесть локальной копии — зона скилла fpf-integration, не этого; переход на текущую редакцию спеки — отдельная задача.
What ships with it
20 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.
- assets/maturity.py 45 KB runs code
- assets/template-dpf.md 6.5 KB
- assets/template-source-pack.md 1.1 KB
- assets/test_maturity.py 43 KB runs code
- frameworks/DPF-ADVERSARIAL-REVIEW/assets/apply-prompt.md 11 KB
- frameworks/DPF-ADVERSARIAL-REVIEW/DPF.md 62 KB
- frameworks/DPF-ADVERSARIAL-REVIEW/references/critic-review.md 19 KB
- frameworks/DPF-ADVERSARIAL-REVIEW/references/scope.md 4.3 KB
- frameworks/DPF-ADVERSARIAL-REVIEW/references/sota-research.md 37 KB
- frameworks/DPF-ADVERSARIAL-REVIEW/references/source-pack.md 23 KB
- frameworks/DPF-ADVERSARIAL-REVIEW/references/theses-antitheses.md 38 KB
- frameworks/DPF-KNOWLEDGE-CURATION/assets/apply-prompt.md 5.9 KB
- frameworks/DPF-KNOWLEDGE-CURATION/DPF.md 65 KB
- frameworks/DPF-KNOWLEDGE-CURATION/references/critic-review.md 17 KB
- frameworks/DPF-KNOWLEDGE-CURATION/references/scope.md 5.5 KB
- frameworks/DPF-KNOWLEDGE-CURATION/references/sota-research.md 41 KB
- frameworks/DPF-KNOWLEDGE-CURATION/references/source-pack.md 19 KB
- frameworks/DPF-KNOWLEDGE-CURATION/references/theses-antitheses.md 68 KB
- references/lifecycle.md 16 KB
- references/method.md 32 KB
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.
- 5d ago First seen · 92 lines · 175 tokens per session scan A c483325dd967
dpf-authoring is a skill published in the GitHub repository spumer/i-m-senior-developer (11 stars, last pushed 3d ago), licensed MIT. It adds 175 tokens to every session and 2,780 once invoked, about $0.0009 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.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…