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 commands/spumer/i-m-senior-developer/plan-featgit clone --depth 1 https://github.com/spumer/i-m-senior-developerWhat 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 | $0.00037 | $0.00566 |
| Opus 5 | $0.00018 | $0.00283 |
| Sonnet 5 | $0.00007 | $0.00113 |
| Haiku 4.5 | $0.00004 | $0.00057 |
Grade A, and why
plan-feat 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 2d 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.
What it actually says
Активируй скилл product-discovery с видом документа feature и выполни его порядок работы от начала до конца. Для этого вида скилл загружает references/feature-mode.md.
Разбор $ARGUMENTS:
- Свободное описание одной фичи — проработка требований новой фичи.
- Путь к замыслу с решённым исходом
feature— проработка фичи из замысла; замысел передаётся вsyncфлагом--parent. - Путь к
ROADMAP.mdс идентификатором элемента — фича для этого элемента порядка. - Путь к существующей фиче (
README.mdили каталогу фичи) — продолжение или пересмотр; сначала посмотри состояние черезinspect. - Пустой аргумент — начни диалог с вопроса, что за фича.
Информационные вопросы задаются прозой порциями по два–четыре; выбор из вариантов и значимые решения — через AskUserQuestion по протоколу значимого решения скилла.
Успешный запуск всегда записывает результат в features/FEAT-NNNN-<slug>/README.md. После успешной записи в чате — только короткий итог по формату скилла: вид, путь и версия, два–четыре главных исхода, цепочка дальше. Полный документ в чат не дублируется.
Цепочка после готовой фичи (readiness: ready):
/plan features/FEAT-NNNN-<slug>/README.md— архитектура по требованиям;/plan features/FEAT-NNNN-<slug>/ARCHITECTURE.md— план выполнения по архитектуре;/plan-do features/FEAT-NNNN-<slug>/— реализация по плану.
Цепочку назови в итоге; не запускай её сам. Метод проработки и правила остановки — в скилле; не повторяй их здесь. При ошибке записи следуй разделу «Ошибка записи» скилла: подготовленное тело документа — запасной результат.
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.
- 2d ago First seen · 29 lines · 37 tokens per session scan A 661f02f52c24
plan-feat is a command published in the GitHub repository spumer/i-m-senior-developer (11 stars, last pushed 11d ago), licensed MIT. It adds 37 tokens to every session and 566 once invoked, about $0.0002 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
constitution
Create or update the project constitution from interactive or provided principle inputs.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.