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 skills add ailiheizi/workflow-to-skill --skill project-launch-content-packgit clone --depth 1 https://github.com/ailiheizi/workflow-to-skillWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/ailiheizi/workflow-to-skill/project-launch-content-pack)<a href="https://agentmods.dev/skills/ailiheizi/workflow-to-skill/project-launch-content-pack"><img src="https://agentmods.dev/badge/skills/ailiheizi/workflow-to-skill/project-launch-content-pack/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/ailiheizi/workflow-to-skill/project-launch-content-pack"><img src="https://agentmods.dev/badge/skills/ailiheizi/workflow-to-skill/project-launch-content-pack.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00061 | $0.01879 |
| Opus 5.5 | $0.00024 | $0.00752 |
| Sonnet 5.5 | $0.00012 | $0.00376 |
| Haiku 4.5 | $0.00006 | $0.00188 |
Grade A, and why
project-launch-content-pack 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 1mo 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 — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Launch Content Pack
Create a reviewable launch package from real source material. Adapt one factual message to Xiaohongshu and Zhihu without operating either platform.
The workflow ends with content and a manual publication checklist. It must not log in, read browser cookies, upload media, publish, schedule, comment, like, follow, or modify an account. A later publishing request is a separate task with separate capabilities and authorization.
Outcome And Inputs
The completed package must let a person understand the source basis, review every material claim, and manually publish platform-appropriate content.
Establish:
- Source material: one or more supplied files, URLs, pasted documents, or repository paths. At least one readable source is required.
- Launch goal: what the content should make the audience understand or do.
- Audience: the people whose language, prior knowledge, and concerns shape the explanation.
- Platforms: default to both Xiaohongshu and Zhihu; accept either one.
- Language: default to the user's language.
- Tone and call to action: optional. Infer a restrained, factual default when omitted.
- Requested depth or length: optional. Respect an explicit platform limit; otherwise produce a bounded, publication-ready package rather than an exhaustive source restatement.
- Evidence policy: default to source-only. Use external research only when the user asks for it and the Harness exposes a real read/search capability.
Ask for clarification when the launch goal, audience, or source identity is materially ambiguous. The Agent may choose harmless formatting, ordering, headline variants, and visual direction.
Capabilities And Harness Bindings
The required semantic capability is read-only access to the supplied source material plus ordinary text generation and result delivery.
In the observed DSH binding, prefer the native read tool for named files and
use glob only when the user supplies a directory but not the relevant files.
Do not use bash merely to duplicate a working file-read tool. If current
public facts are explicitly requested, DSH may use its existing web_search
and public HTTP capability, but those are optional and were not required by
the representative source-only case.
What ships with it
6 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.
- 1mo ago First seen · 193 lines · 61 tokens per session scan A cb14a9c7cd13
project-launch-content-pack is a skill published in the GitHub repository ailiheizi/workflow-to-skill (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 61 tokens to every session and 1,879 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-16.
Other skills, from other repositories
sdlc-accelerate
End-to-end SDLC ramp-up from idea to construction-ready with automated phase transitions.
agent-loop
Detect requests for iterative autonomous agent loops and route to the appropriate loop executor.
cross-task-learner
Enable agent loops to learn from similar past tasks and share patterns across loops.
infer-completion-criteria
Infer measurable completion criteria for an agent-loop task from project docs, code, and AIWG standards when the user has not supplied --completion explicitly.
aiwg-language-map
AIWG addons + extensions language map — categories, curated discover phrases, and per-bundle pointers covering everything beyond the framework quickrefs.
aiwg-regenerate-claude
Regenerate CLAUDE.md for Claude Code with hook file architecture.