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/maxtechera/ship/feedback-loopnpx skills add maxtechera/ship --skill feedback-loopgit clone --depth 1 https://github.com/maxtechera/shipWhat 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 | $0.00025 | $0.00684 |
| Opus 5 | $0.00013 | $0.00342 |
| Sonnet 5 | $0.00005 | $0.00137 |
| Haiku 4.5 | $0.00003 | $0.00068 |
Grade A, and why
content-feedback-loop 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Content Feedback Loop
Every piece of content teaches something. This skill ensures those lessons are captured and applied.
SHIP → MEASURE → LOG → APPLY → next cycle
Phase 1: Ship (immediately after publishing)
When a piece publishes:
- Record the live URL / permalink
- Note the publish timestamp and platform
- Set the measurement window (when to check metrics: 24h / 7d)
- Flag any pre-publish notes (what we expected, what we tried differently)
Phase 2: Measure (when metrics come in)
Pull metrics from the live asset (use content-measure):
- Capture day-1 and week-1 snapshots
- Compare against your baseline and batch average
- Note what's above and below expectations
Phase 3: Log (extract the pattern)
For each piece that underperformed or overperformed, extract a pattern:
Date: YYYY-MM-DD
Asset: [URL or ID]
Result: [metric + value vs baseline]
Pattern: [what this tells us — the repeatable insight, not the one-time fact]
Category: hook / format / timing / platform / topic / CTA
Pattern categories:
| Category | Log here when... |
|---|---|
hook_works |
A hook type drove above-average 3s retention |
hook_fails |
A hook type caused early drop-off |
format_wins |
A specific format (carousel, reel, thread) outperformed batch |
timing_pattern |
Posting time correlated with reach |
topic_resonance |
Specific topic cluster drove saves/shares |
cta_conversion |
A specific CTA wording drove above-average clicks |
Phase 4: Apply (route the learning)
Route each pattern to the right destination:
| Pattern type | Route to |
|---|---|
| Hook formula | Storyboard → hook section rules |
| Format preference | Waterfall → platform priority order |
| Voice/copy | Copy skill → voice constraints |
| Timing | Distribution → schedule defaults |
| Topic cluster | Compose → next pillar topic shortlist |
| CTA wording | Offer + copy skills |
Routing format:
Pattern: [insight]
Route: [skill/file] → [specific section]
Change: [what to update or add]
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 · 88 lines · 25 tokens per session scan A 076c18c457a0
content-feedback-loop is a skill published in the GitHub repository maxtechera/ship (2 stars, last pushed 4mo ago), licensed MIT. It adds 25 tokens to every session and 684 once invoked, about $0.0001 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
article-writing
Write articles, guides, blog posts, tutorials, newsletter issues, and other long-form content in a distinctive voice derived from supplied examples or brand guidance. Use when the user wants polished written content longer than a paragraph, especially when voice consistency, structure, and credibility matter.
a-evolve
Apply A-Evolve's agentic evolution methodology to improve AI agent performance across runs. Use when the user wants to diagnose agent failures, generate targeted skills from error patterns, evolve system prompts, or accumulate episodic knowledge. Works standalone or inside AutoResearchClaw pipelines. Triggers on…
hive.chart-creation-foundations
Required reading whenever any chart tool is available. Teaches the one-tool embedding contract (call chartrender → live chart appears in chat AND a downloadable PNG lands in the queen session dir), the ECharts (data viz) vs Mermaid (structural diagrams) decision, the BI/financial-grade aesthetic baseline (no…
📝 任务完成后归档
重要提醒: 每次完成复杂调试或开发任务后，主动执行此流程！ 将学到的经验归档为 skill，供以后参考。不要等用户提醒。.
deck-course-module
暖纸背景 + Playfair, 左侧学习目标常驻, 含 MCQ 自测页.
code-documenter
Use when adding docstrings, creating API documentation, or building documentation sites. Invoke for OpenAPI/Swagger specs, JSDoc, doc portals, tutorials, user guides.