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/checknpx skills add bacsystem/parallel-plan-executor --skill checkgit 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 | $0.00046 | $0.00726 |
| Opus 5 | $0.00023 | $0.00363 |
| Sonnet 5 | $0.00009 | $0.00145 |
| Haiku 4.5 | $0.00005 | $0.00073 |
Grade A, and why
check 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
cys:check
Two disciplines in one skill: reviewing someone else's change adversarially, and verifying your own claims before you make them.
Announce at start: "Using cys:check to review/verify this work."
Reviewing a change
Treat the implementer's report as unverified claims — verify against the diff, never against the narrative. Read the actual change once, fully.
Structure every review as two independent verdicts:
- Spec compliance — verdict
PASSorFAIL. Findings categorized as Missing / Extra / Misunderstood, each withfile:line. - Code quality — verdict
APPROVEDorNEEDS_FIXES. Findings categorized as Critical (must fix) / Important (should fix) / Minor (nice to have), each withfile:line. Hold the change toreferences/code-standards.md(naming, unit size, YAGNI, dead code, comments, test hygiene) — a violation is a finding, not a style opinion.
Both verdicts are always required; a beautiful implementation of the wrong thing FAILs, an ugly implementation of the right thing may PASS with NEEDS_FIXES.
For a whole-branch (cross-task) review, structure it as: Strengths / Issues (Critical, Important, Minor — each with file:line) / Recommendations / Assessment ("Ready to merge? yes/no" with reasoning). Look specifically for cross-boundary defects a per-task review cannot see: interface mismatches, duplicated logic, contract drift.
Deferring a finding
When the user responds to a finding with anything other than fixing it
now (e.g. "later", "not now", "leave it") — whether from a per-task
review, a whole-branch review, or a standalone cys:check run — append
it to <repo>/.cys/pending.md: under ## Bugs for broken/incorrect
behavior, or ## Gaps for missing/deferred scope. Create the file with
the standard skeleton first if it doesn't exist yet:
# Pendientes
## Bugs
## Gaps
## Tareas
Keep the finding's own wording and file:line. Never touch ## Tareas
— that section is free-form user/agent notes, not review output.
What ships with it
1 file 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.
- yesterday First seen · 78 lines · 46 tokens per session scan A 529886216a4f
check is a skill published in the GitHub repository bacsystem/parallel-plan-executor (2 stars, last pushed 1mo ago), licensed MIT. It adds 46 tokens to every session and 726 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.