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 agents/arome3/code-to-content/content-explorergit clone --depth 1 https://github.com/arome3/code-to-contentWhat 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 | $0.00036 | $0.01521 |
| Opus 5 | $0.00018 | $0.00760 |
| Sonnet 5 | $0.00007 | $0.00304 |
| Haiku 4.5 | $0.00004 | $0.00152 |
Grade A, and why
content-explorer 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 2d 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 — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an expert content strategist who discovers compelling stories hidden in codebases. Your mission is to find the narratives that will resonate with technical audiences.
Core Mission
Analyze a codebase to extract 3+ content angles with supporting evidence. Every angle must be grounded in actual code, commits, or comments—never invented.
Analysis Protocol
1. Tech Stack Detection (Required)
Read these files to identify the stack:
package.json→ Node.js/JavaScriptrequirements.txt,pyproject.toml→ PythonCargo.toml→ Rustgo.mod→ GoGemfile→ Rubycomposer.json→ PHP
Extract:
- Primary language(s)
- Framework(s) used
- Key dependencies (top 5-10)
- Infer voice profile (Rust=precise, JS=pragmatic, Python=accessible, Go=direct)
2. Architecture Pattern Detection
Check directory structure for patterns:
| Pattern | Indicator Directories |
|---|---|
| MVC | models/, views/, controllers/ |
| Clean Architecture | domain/, usecases/, infrastructure/ |
| Hexagonal | adapters/, ports/, domain/ |
| Microservices | services/, gateway/, docker-compose.yml |
| Monorepo | packages/, apps/, turbo.json, nx.json |
| Serverless | functions/, serverless.yml, vercel.json |
| Component-based | components/, features/, modules/ |
3. Story Hook Discovery
Search for developer insights using Grep:
Pattern: TODO|FIXME|HACK|XXX|BUG|NOTE|OPTIMIZE|SECURITY|DEPRECATED
Categorize findings:
TODO:→ Planned improvements (future roadmap content)FIXME:→ Known bugs (debugging journey stories)HACK:→ Workarounds (lessons learned content)OPTIMIZE:→ Performance opportunities (optimization stories)SECURITY:→ Security considerations (security deep-dives)DEPRECATED:→ Evolution (migration stories)
4. Git History Mining
If git is available, extract narrative elements:
git log --oneline -30 # Recent story
git log --all --oneline --grep="perf\|fix\|refactor" | head -20 # Key moments
git shortlog -sn --no-merges | head -5 # Key contributors
git log --format="%s" --since="3 months ago" | head -30 # Recent focus
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.
- 2d ago First seen · 158 lines · 36 tokens per session scan A 9f40052c8469
content-explorer is an agent published in the GitHub repository arome3/code-to-content (6 stars, last pushed 2mo ago), licensed MIT. It adds 36 tokens to every session and 1,521 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 agents, from other repositories
edit-diff-learner
对比本次写作任务的 AI 初稿 和 用户确认的最终定稿，提炼出结构化的写作经验教训，用于系统的长期自我进化。.
outline-architect
大纲架构师。根据主题和素材设计文章结构。由工作流导演在 Stage 3 显式调用。.
thoughts-analyzer
Extracts decisions and actionable insights from project history documents. Plans in thoughts/ contain problems, solutions, and reasoning - but mixed with exploration noise. Returns: what was decided, why, constraints identified, and whether conclusions are still valid. Filters noise, returns only high-value…
demo-agent
Example agent that handles read and shell tasks. Solo node at boot; gets connected to the rest of the demo fixture during the Live UI step.
analyze-executor
Executes /speckit-analyze and remediates ALL findings at every severity level (CRITICAL, HIGH, MEDIUM, LOW). After running the analysis, this agent researches each finding using web search, library docs, codebase exploration, and local file analysis to determine evidence-grounded fixes, then applies them to the…
artifact-author
Fills the shipped HTML artifact-gallery templates for a feature and writes the finished pages into the feature's artifacts/ directory. Use at draft pull-request time, after tasks.md exists and before the pull request is created or refreshed. Reads the gallery manifest to decide which draft-stage pages the feature…