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/plannpx skills add bacsystem/parallel-plan-executor --skill plangit 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 | $0.00052 | $0.01497 |
| Opus 5 | $0.00026 | $0.00749 |
| Sonnet 5 | $0.00010 | $0.00299 |
| Haiku 4.5 | $0.00005 | $0.00150 |
Grade A, and why
plan 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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
cys:plan
Write an implementation plan a zero-context engineer could execute: bite-sized tasks, exact paths, complete code, TDD, frequent commits. The plan doubles as machine input — the parallel-plan-executor parses its task blocks into a dependency graph, so format discipline is load- bearing, not cosmetic.
Announce at start: "Using cys:plan to write the implementation plan."
Save plans to: docs/cys/plans/YYYY-MM-DD-<feature-name>.md
(user preferences for location override this default).
Plan header
Every plan MUST start with:
# [Feature Name] Implementation Plan
> **For agentic workers:** execute this plan with the
> parallel-plan-executor Workflow (cys:run / the /cys:run-plan command).
> Steps use checkbox (`- [ ]`) syntax for tracking.
**Goal:** [one sentence]
**Architecture:** [2-3 sentences]
**Tech Stack:** [key technologies]
## Global Constraints
[Project-wide requirements, one line each, exact values copied
verbatim from the spec. Every task implicitly includes this section.]
---
Task format — the parser contract
### Task N: [Component Name]
**Files:**
- Create: `exact/path/to/file.js`
- Modify: `exact/path/to/existing.js`
- Test: `tests/exact/path/to/test.js`
**Interfaces:**
- Consumes: [backticked symbols from earlier tasks — exact signatures]
- Produces: [backticked symbols later tasks rely on]
Hard rules (the executor's parser depends on them):
- Task headers are exactly
### Task N: Title— sequential integer ids, never duplicated. - Only backticked symbols count in Consumes/Produces; loose prose is
ignored by the parser. Backtick every real interface (
createWidget(),src/db.js); never backtick filler words. - One entry per line in Consumes/Produces — a value wrapping onto a second line is silently lost by the parser.
Consumes: Nonemeans an empty list; write it when a task is independent. Both the**Files:**and**Interfaces:**headers themselves must always be present, even for a task with an empty list — omitting either entirely (e.g. a typo like**Interface:**or**File:**) silently drops that task from the corresponding inference (symbol-based dependencies, or file-based serialization); the parser warns when a header is missing, but write the section explicitly rather than relying on that warning.- Two tasks touching the same file are automatically serialized by the executor; design task boundaries so files are disjoint whenever possible — disjoint tasks run in parallel.
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 · 139 lines · 52 tokens per session scan A 0abc6fb8edc6
plan is a skill published in the GitHub repository bacsystem/parallel-plan-executor (2 stars, last pushed 1mo ago), licensed MIT. It adds 52 tokens to every session and 1,497 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.