Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
Wrote 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/xiaotonng/pikiloom/promote)<a href="https://agentmods.dev/skills/xiaotonng/pikiloom/promote"><img src="https://agentmods.dev/badge/skills/xiaotonng/pikiloom/promote.svg" alt="Measured on agentmods" 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 | $0.00084 | $0.03094 |
| Opus 5 | $0.00042 | $0.01547 |
| Sonnet 5 | $0.00017 | $0.00619 |
| Haiku 4.5 | $0.00008 | $0.00309 |
Grade A, and why
promote 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 6d 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 — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitHub Promotion Workflow
This skill targets the open issues of same-space projects (local coding agent ↔ IM / mobile / remote console) — where users have already self-identified as needing this category of tool. We share pikiloom as another option; we never position against the host project.
This file holds GitHub-specific mechanics only (which repos, which issues, how to post). All product
copy, differentiators, honesty bounds, tone, language, skeleton, and anti-patterns come from
../_promo/pitch.md — do not duplicate or edit copy here. Dedup / guardrails /
posting-posture / measurement come from the shared core:
| 关注点 | 位置 |
|---|---|
| 产品话术 SSOT | _promo/pitch.md（§9 表 github 列 = 本渠道机制差异） |
| 去重（写时强制） | _promo/registry.py（channel = github） |
| 护栏（每仓上限/日配额/变体/熔断/deny_repos） | _promo/guard.py |
| 飞书推送 / 度量 | _promo/push_feishu.py / _promo/measure.py |
| 无人值守编排 + posture | _promo/orchestrate.md |
| 旋钮 | _promo/config.json → channels.github |
运行根目录：
cd /Users/admin/Desktop/project/pikiloom。脚本前缀：.pikiloom/skills/_promo/。
GitHub 渠道的铁律
- 只打 feature-request / 用户提问 issue，绝不打 bug 报告。 "能加 X 吗" 是开放问题，分享别的工具已有
X 是正当同行信息；bug 报告是宿主实现的封闭范围，进去推等于批评。
guard.py不知道 issue 类型 —— 这一条 靠筛选阶段把关。 - 每仓终身 ≤ 2 条（
config.jsonper_repo_lifetime_cap）。历史上chenhg5/cc-connect13 条、RichardAtCT/claude-code-telegram10 条 —— 这种集中度正是 AUP §4「coordinated inauthentic activity」 要抓的轮廓。guard.py会按 registry 里的历史强制拦截超限的仓。 - 不打上游本体仓（
anthropics/claude-code等，见deny_repos）—— 不是同类桥接，曝光最高、有官方 triage、风险最大。历史误打了 14 条，停止。guard.py直接 deny。 - 每条独立起草 + 必带披露行（"I'm building / 我在做 pikiloom"）。披露既是诚实也是护身符；boilerplate
翻译版仍是 boilerplate，
guard.py变体检查会拦。
Step 1: 预检
cd /Users/admin/Desktop/project/pikiloom
python3 .pikiloom/skills/_promo/guard.py caps # github 今日剩余配额；为 0 则今天不跑
Step 2: 主路径 — 同领域项目 issue
walk 下列同类项目的 issue tracker（pikiloom 原生支持 Telegram/Feishu/WeChat/Slack/Discord/DingTalk/WeCom， 所有 IM-bridge 仓都是同渠道同类）。bucket 内并行，按时间排序，忽略 >90 天且无活动的。
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.
- 6d ago First seen · 172 lines · 84 tokens per session scan A 0f36d1c2cc71
promote is a skill published in the GitHub repository xiaotonng/pikiloom (294 stars, last pushed 5d ago), licensed MIT. It adds 84 tokens to every session and 3,094 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
shap
Model interpretability and explainability using SHAP (SHapley Additive exPlanations). Use this skill when explaining machine learning model predictions, computing feature importance, generating SHAP plots (waterfall, beeswarm, bar, scatter, force, heatmap), debugging models, analyzing model bias or fairness, comparing…
torch-geometric
Graph Neural Networks (PyG). Node/graph classification, link prediction, GCN, GAT, GraphSAGE, heterogeneous graphs, molecular property prediction, for geometric deep learning.
rowan
Cloud-based quantum chemistry platform with Python API. Preferred for computational chemistry workflows including pKa prediction, geometry optimization, conformer searching, molecular property calculations, protein-ligand docking (AutoDock Vina), and AI protein cofolding (Chai-1, Boltz-1/2). Use when tasks involve…
arboreto
Infer gene regulatory networks (GRNs) from gene expression data using scalable algorithms (GRNBoost2, GENIE3). Use when analyzing transcriptomics data (bulk RNA-seq, single-cell RNA-seq) to identify transcription factor-target gene relationships and regulatory interactions. Supports distributed computation for…
denario
Multiagent AI system for scientific research assistance that automates research workflows from data analysis to publication. This skill should be used when generating research ideas from datasets, developing research methodologies, executing computational experiments, performing literature searches, or generating…
context-recovery
Recovers project handoff context from local Codex, Claude Code, Gemini, CodeBuddy, and codexmate-derived sessions. Use when the user asks what happened in prior project/PR/branch/file/error work, needs a handoff brief, wants old decisions or validations recovered, or asks to summarize cross-session project activity…