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/guidenpx skills add bacsystem/parallel-plan-executor --skill guidegit 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 | $0.00045 | $0.01284 |
| Opus 5 | $0.00023 | $0.00642 |
| Sonnet 5 | $0.00009 | $0.00257 |
| Haiku 4.5 | $0.00005 | $0.00128 |
Grade A, and why
guide 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
cys:guide
cys is a development methodology with parallel execution at its core. Five stages, five skills — each stage's output is the next stage's input.
The flow
| Stage | Skill | In → Out |
|---|---|---|
| 1. Design | cys:design |
idea → approved spec (docs/cys/specs/) |
| 2. Plan | cys:plan |
spec → parser-ready plan (docs/cys/plans/) |
| 3. Run | cys:run — the parallel-plan-executor Workflow (/cys:run-plan, or /cys:flow from an idea) |
plan → implemented, reviewed, merged task branches |
| 4. Check | cys:check |
change → verdicts (spec PASS/FAIL + quality APPROVED/NEEDS_FIXES) |
| 5. Ship | cys:ship |
working tree → Conventional Commit, SemVer bump, PR |
See docs/diagram/flujo-cys-ecosystem.mmd for this same flow as a
diagram, with each stage's input/output artifact and the two human gates
(spec approval, PR merge).
Stage 3 is what makes cys different: independent plan tasks execute in PARALLEL via a dependency DAG inferred from each task's Consumes/Produces block — not one at a time. Stage 4 runs automatically inside stage 3 for every task (adversarial review, one fix round); invoke it standalone for ad-hoc reviews. Stage 5's PR merge is always a human gate — agents never merge PRs.
Stage 5 overlaps with stage 3 when openPr: true was requested. The
Workflow's own Handoff agent (part of stage 3) already does everything
cys:ship would do — classify commits, compute the SemVer bump, write
the PR title/body, push, create the PR — because the sandboxed Workflow
script cannot invoke the Skill tool itself, so it carries a hand-rolled
copy of the same conventions instead of calling cys:ship directly.
Invoke cys:ship only when stage 3 ran without openPr: true (it
just leaves handoff.md with suggestions, nothing pushed), or for any
change that never went through cys:run at all. Running both after an
openPr: true run would just duplicate the PR-creation work.
On platforms other than Claude Code (Cursor, Gemini CLI), cys:run
isn't available — only stage 3's automated DAG scheduling, adversarial
review, and serialized merging are Claude-Code-only. After cys:plan
produces a plan there, execute its tasks yourself in dependency order:
one at a time, or by hand-dispatching the platform's own subagents per
task, without cys:run's orchestration.
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 · 107 lines · 45 tokens per session scan A fc298a940531
guide is a skill published in the GitHub repository bacsystem/parallel-plan-executor (2 stars, last pushed 1mo ago), licensed MIT. It adds 45 tokens to every session and 1,284 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 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.