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/bacsystem/parallel-plan-executor/designnpx skills add bacsystem/parallel-plan-executor --skill designgit clone --depth 1 https://github.com/bacsystem/parallel-plan-executorWhat 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 | $0.00060 | $0.00721 |
| Opus 5 | $0.00030 | $0.00360 |
| Sonnet 5 | $0.00012 | $0.00144 |
| Haiku 4.5 | $0.00006 | $0.00072 |
Grade A, and why
design 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 yesterday.
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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
cys:design
Turn an idea into an approved design spec through natural collaborative dialogue. Understand first, propose second, write the spec last.
Announce at start: "Using cys:design to shape this idea into a spec."
Process
- Explore context — read the relevant files, docs and recent commits of the target repo before asking anything.
- Scope check — if the request spans multiple independent subsystems, say so and help decompose it first; one spec per coherent sub-project.
- Clarifying questions — ONE question per message. Prefer multiple choice. Cover purpose, constraints, and success criteria. Stop asking when you can state what you are building in two sentences.
- Propose 2-3 approaches — with trade-offs, leading with your recommendation and why.
- Present the design in sections — scale each section to its complexity; ask after each whether it looks right. Cover: architecture, components, data flow, error handling, testing.
- Write the spec to
docs/cys/specs/YYYY-MM-DD-<topic>-design.md(user preferences for location override this default) and commit it. - Self-review the spec — placeholders ("TBD", vague requirements), internal contradictions, scope creep, ambiguous requirements readable two ways. Fix inline.
- User review gate — ask the user to review the written spec file. Only proceed on explicit approval.
- Hand off to cys:plan — the ONLY next step after approval is invoking cys:plan to write the implementation plan.
Design principles
- Decisions the user already made are settled — do not re-litigate them.
- YAGNI ruthlessly: strike features the goal does not need.
- Prefer small units with one clear purpose and well-defined interfaces; if internals cannot change without breaking consumers, redraw the boundaries.
- In existing codebases, follow the established patterns; propose targeted improvements only where existing problems block the current work.
- Environment-dependent constraints are verified, not inherited. A prior
spec's finding about this sandbox (a blocked binary, no Docker, etc.)
does not automatically apply to a different stack or a later run —
check it empirically for this project (e.g.
docker info, whether the relevant binary/service actually responds) before letting it drive a decision like "tests can only use mocks."
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.
- yesterday First seen · 66 lines · 60 tokens per session scan A ef5099241c86
design is a skill published in the GitHub repository bacsystem/parallel-plan-executor (2 stars, last pushed 1mo ago), licensed MIT. It adds 60 tokens to every session and 721 once invoked, about $0.0003 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
sql-reporting
Conventions and review steps for writing analytics SQL against the warehouse. Use whenever the task involves querying tables, building a report, or aggregating metrics.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
verify-security
安全校验关卡。自动扫描代码安全漏洞，检测危险模式，确保安全决策有文档记录。当用户提到安全扫描、漏洞检测、安全审计、代码安全、OWASP、注入检测、敏感信息泄露时使用。在新建模块、安全相关变更、攻防任务、重构完成时自动触发。.
development
开发语言能力索引。Python、Go、Rust、TypeScript、Java、C++、Shell。当用户提到编程、开发、代码、语言时路由到此。.
post-build-flow
Handles workflow verification and setup after build-workflow succeeds, or when the message contains workflow-verification-follow-up or workflow-setup-required. Load after direct builds, when verificationReadiness requires action, or on orchestrator verify/setup follow-up turns.
n8n:human-like-code-review
Reviews a GitHub pull request like a thoughtful human reviewer and writes the feedback to a markdown file. Prioritizes context, architecture fit, solution complexity, bugs, security edge cases, and missing tests. Use when given a PR URL to review, or when the user says /human-like-code-review.