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/andrewcigan/vibe-dev-plugin/featurenpx skills add andrewcigan/vibe-dev-plugin --skill featuregit clone --depth 1 https://github.com/andrewcigan/vibe-dev-pluginWhat 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 | $0.00081 | $0.02938 |
| Opus 5 | $0.00041 | $0.01469 |
| Sonnet 5 | $0.00016 | $0.00588 |
| Haiku 4.5 | $0.00008 | $0.00294 |
Grade A, and why
feature scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/feature
Запуск одной фичи. WIP=1 enforced — другую фичу взять нельзя пока эта не passing.
Pre-flight checks
Check 0: Enforcement жив? (v6.2 F2; discipline-слой, несущий канал — pre-commit backstop)
P="$(cat .harness/profile 2>/dev/null)"; HB=.harness/hooks-heartbeat
case "$P" in pending-*) echo "❌ профиль $P не подтверждён живым хуком — enforcement НЕ активен"; esac
[ -f "$HB" ] && [ $(( $(date +%s) - $(awk '{print $1;exit}' "$HB") )) -le 1800 ] \
|| echo "❌ heartbeat несвежий/отсутствует — хуки в этой сессии НЕ работают"
ls .harness/hook-crashes/ 2>/dev/null && echo "⚠️ сторожа падали — см. /doctor"
Любая строка с ❌ → STOP: запусти /doctor, почини активацию, потом возвращайся к фиче.
Работать над фичей при мёртвых сторожах = «харнес не поднялся» (главный провал аудита 06-10).
Check 1: WIP=1
# В feature_list.json должна быть ровно одна active или ноль
python3 -c "
import json
d = json.load(open('feature_list.json'))
active = d.get('active')
if active is not None and active != '<this-feature-id>':
print(f'❌ WIP=1 violated: feat \"{active}\" already active. Закрой её через /verify до passing или /handoff с paused.')
exit(1)
"
Если нарушено — STOP, скажи пользователю.
Check 2: Feature существует в captured/up_next
Если фича в done — спроси пользователя зачем заново.
Если фича в superseded/rejected — STOP.
Check 3: Зависимости
# Если feat.dependencies = ["feat-001", "feat-002"] — все должны быть в done
Если нет — предложить взять зависимости сначала.
Размер и ПОВЕРХНОСТЬ фичи → light/heavy path
Из feature_list.json смотрим size_estimate И surface (v6.2 F5 — урок П2 аудита:
«зелёные тесты лгут» именно на интерфейсных фичах, которые по размеру проскакивали мимо критика):
- S (<1 час, ~30 строк, 1 файл) → light path (syntax + scope check, без dual critique)
- M (1-4 часа, 30-200 строк) → medium path (single critic + verify)
- L (1+ день, >200 строк) → heavy path (dual critique + 4-layer verify)
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.
- 3d ago First seen · 196 lines · 81 tokens per session scan A d3c07e5bfbb6
feature is a skill published in the GitHub repository andrewcigan/vibe-dev-plugin (5 stars, last pushed 1mo ago), licensed MIT. It adds 81 tokens to every session and 2,938 once invoked, about $0.0004 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
harness-engineering-guide
Audit, design, and implement AI agent harnesses for any codebase. A harness is the constraints, feedback loops, and verification systems surrounding AI coding agents — improving it is the highest-leverage way to improve AI code quality. Three modes: Audit (scorecard), Implement (set up components), Design (full…
google-drive-sheets
Find, read, export, edit, and manage the user's Google Drive, Docs, Sheets, and Slides through per-user OAuth.
github-gitlab
Work with GitHub and GitLab repositories through resident gh/glab/git auth on the agent computer.
harness-creator
Build, audit, and improve harnesses that make AI coding agents reliable: AGENTS.md/CLAUDE.md instruction files, feature/state tracking, verification gates, scope boundaries, session handoff, memory persistence, context budgets, tool-permission safety, and multi-agent coordination. Use this whenever a coding agent is…
miniapp
Build a tiny interactive HTML playground only when someone asks to see, play with, or step through a mechanism.
commit-push-pr
Commit selected local changes, push the branch, and create or update a GitHub pull request with BitFun attribution. Use when the user asks to 提交 PR、提代码、commit and push、开 PR、create a pull request, or wants a Claude Code-like one-command PR publishing flow from BitFun.