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 adityarbhat/feedfwd --skill distillergit clone --depth 1 https://github.com/adityarbhat/feedfwdWrote 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/adityarbhat/feedfwd/distiller)<a href="https://agentmods.dev/skills/adityarbhat/feedfwd/distiller"><img src="https://agentmods.dev/badge/skills/adityarbhat/feedfwd/distiller/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/adityarbhat/feedfwd/distiller"><img src="https://agentmods.dev/badge/skills/adityarbhat/feedfwd/distiller.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 | $0.00000 | $0.00647 |
| Opus 5 | $0.00000 | $0.00324 |
| Sonnet 5 | $0.00000 | $0.00129 |
| Haiku 4.5 | $0.00000 | $0.00065 |
Grade A, and why
distiller 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 8d 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
FeedFwd Knowledge Card Format Specification
================================================================
This skill defines the canonical format for knowledge cards.
It serves as a reference for the distiller subagent and any
component that reads or writes knowledge cards.
How it works in Claude Code:
Skills are reference documents that Claude can consult. They
live in skills//SKILL.md and are discovered automatically.
Unlike agents (which do work), skills provide knowledge.
================================================================
name: distiller description: > Knowledge card format specification for FeedFwd. Defines the structure, fields, and rules for creating and maintaining knowledge cards.
Knowledge Card Format
Each knowledge card is a markdown file with YAML frontmatter stored in
~/.config/feedfwd/knowledge/<category>/<name>.md.
Required YAML Fields
| Field | Type | Description |
|---|---|---|
name |
string | Kebab-case identifier (also the filename without .md) |
source |
string | Original URL, "pasted-text", or "screenshot" |
captured |
date | ISO date when the card was created (YYYY-MM-DD) |
category |
string | One of the predefined categories or a new one |
score |
float | Relevance score, 0.0–1.0. New cards start at 0.50 |
times_surfaced |
int | How many sessions this card has been injected into |
times_useful |
int | How many times the user marked it as useful |
triggers.keywords |
list | Words that signal this card is relevant |
triggers.file_patterns |
list | Glob patterns for relevant file types |
triggers.task_types |
list | Task categories where this applies |
injection_tokens |
int | Pre-computed token count of the Injection Text |
Required Markdown Sections
- ## Insight — 2-3 sentences. Human-readable summary. Never injected.
- ## Injection Text — Direct instruction to Claude. Hard cap: 250 tokens. Written as actionable guidance, not article summary.
- ## Example — Before/after demonstrating the technique in action.
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.
- 8d ago First seen · 68 lines · 0 tokens per session scan A 9b7c7fa98f14
distiller is a skill published in the GitHub repository adityarbhat/feedfwd (2 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 647 tokens. 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…