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/baodq97/open-plugin/vbouncenpx skills add baodq97/open-plugin --skill vbouncegit clone --depth 1 https://github.com/baodq97/open-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 | $0.00177 | $0.06163 |
| Opus 5 | $0.00088 | $0.03082 |
| Sonnet 5 | $0.00035 | $0.01233 |
| Haiku 4.5 | $0.00018 | $0.00616 |
Grade A, and why
vbounce 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.
How it starts
The opening of the file, as written. The whole thing — 466 lines — stays where its author put it; the contents beside it link to each section on GitHub.
V-Bounce SDLC Orchestrator v5.1
Agent-first SDLC framework with explicit contracts, shared workspace, state management, unified TDD, and per-phase specialized QG agents.
Based on arXiv 2408.03416 (Hymel, 2024): AI handles implementation, humans shift to validators/verifiers.
Core Principles
- Agent-First — agents are the execution units; orchestrator manages state and contracts
- Explicit Contracts — every agent declares input/output files with validation patterns
- Shared Workspace — all artifacts live in
.vbounce/cycles/{cycle_id}/ - State Machine — orchestrator reads/writes state.yaml, determines next action
- Multi-Layer QA — input validation, output validation, semantic QG, cross-agent compatibility
- 7-Activity Phase Anatomy — see references/phase-anatomy.md
- Technology-Aware — detect project tech stack and inject framework context into all agent dispatches
Cycle Initialization
When the user provides a PRD or says "start vbounce cycle":
- Generate cycle ID:
CYCLE-{PROJECT}-{YYYYMMDD}-{SEQ}(derive PROJECT from directory name, SEQ starts at 001) - Create workspace:
mkdir -p .vbounce/cycles/{cycle_id}/{requirements,design,contracts,implementation,review,deployment,knowledge,quality-gates} - Copy PRD: Write/copy the user's PRD to
.vbounce/cycles/{cycle_id}/prd.md - Tech Stack Detection: Scan the project for manifest files to detect the tech stack:
- Check in order:
package.json(JS/TS),pyproject.toml/requirements.txt(Python),*.csproj(C#),go.mod(Go),Cargo.toml(Rust),pom.xml/build.gradle(Java/Kotlin) - Read
CLAUDE.mdfor explicit tech stack declarations (overrides auto-detection) - If no manifest found, scan top 5 source files for import patterns and file extensions
- Write
{workspace}/tech-context.yamlwith:language,runtime,package_manager,frameworks(list of {name, version, role}),build_tool,install_command,compile_command,test_command,source_dirs,test_dirs,detected_from - Resolve install/compile/test commands per language + package manager — see references/tech-stack-commands.md
- Check in order:
- Framework Context Loading: Based on
tech-context.yaml, check for relevant installed skills:- For each detected framework, search installed skills for matching trigger phrases (skill descriptions contain framework names)
- If match found, read that skill's SKILL.md + key reference files
- Extract: framework patterns, testing conventions, security considerations, known anti-patterns
- Always check:
hallucination-patterns.mdfor entries matching detected ecosystem,coding-standards.mdfor detected language,CLAUDE.mdfor project-specific conventions - If no skill matches any detected framework, graceful degradation: agents work without framework context (tech-context-prompt.md will only contain language + framework names + versions)
- Write
{workspace}/tech-context-prompt.mdwith: primary stack info, key patterns, known hallucination risks, testing conventions
- Initialize state: Write
.vbounce/cycles/{cycle_id}/state.yamlwith v5.1 state schema (all phases including contracts set tonot_started,current_phase: requirements,anatomy_step: input,tech_contextpopulated from detection) - Set active cycle: Write
.vbounce/state.yamlwith justactive_cycle: {cycle_id}andworkspace: .vbounce/cycles/{cycle_id} - Proceed: Begin requirements phase (validate input contract, dispatch requirements-analyst)
What ships with it
16 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.
- references/acceptance-criteria.md 944 B
- references/ambiguity-checklist.md 1.3 KB
- references/approval-matrix.md 1.3 KB
- references/architecture-patterns.md 1.6 KB
- references/coding-standards.md 1012 B
- references/edge-cases.md 1.2 KB
- references/hallucination-patterns.md 6.7 KB
- references/id-conventions.md 1.8 KB
- references/phase-anatomy.md 2.5 KB
- references/quality-criteria.md 1.6 KB
- references/tech-stack-commands.md 1.5 KB
- references/user-story-patterns.md 1.0 KB
- references/workflows-bugfix-track.md 29 KB
- references/workflows-by-role.md 26 KB
- references/workflows-change-request-track.md 38 KB
- references/workflows-hotfix-track.md 27 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.
- 2d ago First seen · 466 lines · 177 tokens per session scan A 61ae1e5a9da0
vbounce is a skill published in the GitHub repository baodq97/open-plugin (4 stars, last pushed 3mo ago), licensed MIT. It adds 177 tokens to every session and 6,163 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
brainstorm-okrs
Brainstorm team-level OKRs aligned with company objectives — qualitative objectives with measurable key results. Use when setting quarterly OKRs, aligning team goals with company strategy, drafting objectives, or learning how to write effective OKRs.
pre-mortem
Run a pre-mortem risk analysis on a PRD or launch plan. Categorizes risks as Tigers (real problems), Paper Tigers (overblown concerns), and Elephants (unspoken worries), then classifies as launch-blocking, fast-follow, or track. Use when preparing for launch, stress-testing a product plan, or identifying what could go…
ab-test-analysis
Analyze A/B test results with statistical significance, sample size validation, confidence intervals, and ship/extend/stop recommendations. Use when evaluating experiment results, checking if a test reached significance, interpreting split test data, or deciding whether to ship a variant.
dummy-dataset
Generate realistic dummy datasets for testing with customizable columns, constraints, and output formats (CSV, JSON, SQL, Python script). Use when creating test data, building mock datasets, or generating sample data for development and demos.
outcome-roadmap
Transform an output-focused roadmap into an outcome-focused one that communicates strategic intent. Rewrites initiatives as outcome statements reflecting user and business impacts. Use when shifting to outcome roadmaps, making a roadmap more strategic, or rewriting feature lists as outcomes.
release-notes
Generate user-facing release notes from tickets, PRDs, or changelogs. Creates clear, engaging summaries organized by category (new features, improvements, fixes). Use when writing release notes, creating changelogs, announcing product updates, or summarizing what shipped.