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/cacheforge-ai/cacheforge-skills/feed-dietnpx skills add cacheforge-ai/cacheforge-skills --skill feed-dietgit clone --depth 1 https://github.com/cacheforge-ai/cacheforge-skillsWrote 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/cacheforge-ai/cacheforge-skills/feed-diet)<a href="https://agentmods.dev/skills/cacheforge-ai/cacheforge-skills/feed-diet"><img src="https://agentmods.dev/badge/skills/cacheforge-ai/cacheforge-skills/feed-diet.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 | $0.00029 | $0.01101 |
| Opus 5 | $0.00015 | $0.00550 |
| Sonnet 5 | $0.00006 | $0.00220 |
| Haiku 4.5 | $0.00003 | $0.00110 |
Grade A, and why
feed-diet scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
🍽️ Feed Diet
Audit your information diet and get a gorgeous report showing what you actually consume.
Trigger
Activate when the user mentions any of:
- "feed diet"
- "information diet"
- "audit my feeds"
- "what am I reading"
- "analyze my HN"
- "reading habits"
- "content diet"
- "feed report"
Instructions
Audit Mode (default)
-
Determine the data source. Ask the user for one of:
- A Hacker News username (e.g., "tosh")
- An OPML file path containing RSS feed subscriptions
-
Fetch the content. Run the appropriate fetch script:
# For HN: bash "$SKILL_DIR/scripts/hn-fetch.sh" USERNAME 100 # For OPML: bash "$SKILL_DIR/scripts/opml-parse.sh" /path/to/feeds.opml -
Classify items. Pipe the fetched items through the classifier:
cat items.jsonl | bash "$SKILL_DIR/scripts/classify.sh" > classified.jsonlThe classifier uses LLM (if ANTHROPIC_API_KEY or OPENAI_API_KEY is set) or falls back to keyword matching.
-
Generate the report. Run the main entry point:
bash "$SKILL_DIR/scripts/feed-diet.sh" audit --hn USERNAME --limit 100 -
Present the report to the user. The output is Markdown — render it directly.
Digest Mode (weekly curated reading)
When the user wants a filtered reading list based on their goals:
bash "$SKILL_DIR/scripts/feed-diet.sh" digest --hn USERNAME --goal "systems programming, distributed systems" --days 7
Quick Reference
| Command | Description |
|---|---|
feed-diet audit --hn USER |
Full diet audit for an HN user |
feed-diet audit --opml FILE |
Full diet audit from RSS feeds |
feed-diet digest --hn USER --goal "X" |
Weekly digest filtered by goals |
Notes for the Agent
- Be conversational. After presenting the report, offer observations like "Looks like you're heavy on news — want me to suggest some deeper technical feeds?"
- Suggest the digest mode if the user seems interested in filtering their reading.
- The report is the star. Don't summarize it — present it in full. It's designed to be screenshot-worthy.
- If classification seems off, mention that setting an LLM API key improves accuracy.
What ships with it
8 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.
- 4d ago First seen · 131 lines · 29 tokens per session scan A 8142dcadbf60
feed-diet is a skill published in the GitHub repository cacheforge-ai/cacheforge-skills (10 stars, last pushed 6mo ago), licensed MIT. It adds 29 tokens to every session and 1,101 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
pilot-discord-bridge
Bidirectional bridge between Pilot Protocol and Discord servers. Use this skill when: 1. You need to send Discord notifications from Pilot agents 2. You want to receive Discord messages in Pilot event streams 3. You're building agents that interact with Discord communities Do NOT use this skill when: - You only need…
pilot-webhook-bridge
Forward Pilot Protocol events to HTTP webhooks for Slack, Discord, PagerDuty, and custom integrations. Use this skill when: 1. You need to forward Pilot events to external services (Slack, Discord, Teams) 2. You need to integrate with monitoring/alerting platforms (PagerDuty, Datadog) 3. You need to trigger external…
factor-research
Factor research framework with IC/IR analysis, quantile backtesting, and factor combination. Suitable for cross-sectional factor evaluation across multiple instruments.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
Workspace Data Analyst
Analyze CSV files in the workspace and summarize insights.
data_analyst
Analyses datasets with professional rigour — statistical summaries, clear narratives, and well-chosen visualisations.