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/fusebase-dev/fusebase-flow/role-disciplinenpx skills add fusebase-dev/fusebase-flow --skill role-disciplinegit clone --depth 1 https://github.com/fusebase-dev/fusebase-flowWhat 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 | $0.00079 | $0.03401 |
| Opus 5 | $0.00039 | $0.01700 |
| Sonnet 5 | $0.00016 | $0.00680 |
| Haiku 4.5 | $0.00008 | $0.00340 |
Grade A, and why
role-discipline 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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Do not re-Read this file if it is already in your context. If this exact SKILL.md body is already present in your context (surfaces that auto-load
.claude/skills/or.agents/skills/), do not Read this file again — seeing the name/description in a skill index does not count. If it is not present, read it once. Delegated sub-agent sessions do not inherit an auto-load: they read it. This exemption covers this file only —references/<role>.mdis a separate required read (§ Per-role scoped loading), and an auto-load never delivers it.Surface truth (AC11, verified): no surface injects this body — Claude Code and Codex supply description/metadata only; Gemini, Copilot, Cursor and delegated sub-agents supply nothing. Read it once when the body is not already in context.
Role discipline
What must I refuse as this role, and how do I phrase it.
Required inputs
| Input | If missing |
|---|---|
| Self-attested role | STOP — attest before any other action |
FLOW_RULES.md (FR-01..FR-27, repo root) |
read at session start down to ## Amendment log (dated history — never load it). FR-09/18/22/23/25/26 also arrive always-on via § Write-time discipline digest (FR-24). |
policies/command-policy.yml |
hooks consult it; don't duplicate the check |
Per-role scoped loading
Read your role's reference file — your don't-list + exact refusal phrasing live there; no auto-load delivers them. Cross-check every action against it. Another role's file: on demand (violation-recovery, or drafting a handoff it consumes).
| Role | Read |
|---|---|
| Product Owner | references/product-owner.md (+ references/architect.md on escalation) |
| AI Developer | references/ai-developer.md |
| Deploy phase | references/deploy.md |
| Architect (standalone) | references/architect.md |
Shared protocols — prohibitions resident, bodies lazy
Each section is a stub carrying its prohibition; all apply to every role (§ Operator Relay is PO-only). Steps, tables, worked examples and recovery narrative are in references/shared-protocols.md — read it when you RUN a protocol, never at session start. A prohibition never lazy-loads.
What ships with it
5 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.
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 · 137 lines · 79 tokens per session scan A fa5f1094b89e
role-discipline is a skill published in the GitHub repository fusebase-dev/fusebase-flow (9 stars, last pushed 7d ago), licensed MIT. It adds 79 tokens to every session and 3,401 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
lov-cli2anything
将已授权观察到的网站 API 转成可验证的 OpenAPI、SDK、Swagger 或任务型 CLI。适用于“把这个网站 API 变成 CLI”“生成可调用 Swagger”以及 “turn observed APIs into a CLI”。.
dsh-plugin-creator
Create a @deepseek-ai/dsh- plugin package end-to-end — choose the extension point or capability seam, scaffold the package, implement the tool/hook/service, and run the repo gates. 触发：新增插件 / 加工具 / 开发 capability。.
sgc-install-ai
为现有或新 App 快速初始化可上线的 AI 功能，可选择本地 Agent Client、MaaS 中转渠道、模型偏好和配套 UI。用户说集成 AI、给 App 加聊天/生成能力、Agent Client、MaaS 或模型选择时使用。.
prompt-pack
Generates a self-contained prompt pack from a spec. Embeds real code patterns from .vibeflow/ so any coding agent (Claude Code, Cursor, Copilot) follows the project's conventions without needing repo context. Use when handing off implementation to a separate session or agent.
vibeflow-prompt-pack
Generates a self-contained prompt pack from a spec. Embeds real code patterns from .vibeflow/ so any coding agent follows the project's conventions. Use when handing off implementation to a separate session or agent.
iblai-api-agent-mcp
MCP connectors for ibl.ai agents, end to end — register MCP servers (featured multi-tenant sharing, enable/disable, OAuth service linkage), manage credential connections with the authtype × scope matrix (org / agent / per-user), wire servers onto an agent, run the OAuth connected-service lifecycle, handle per-user…