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/adityarbhat/feedfwd/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/agents/adityarbhat/feedfwd/distiller)<a href="https://agentmods.dev/agents/adityarbhat/feedfwd/distiller"><img src="https://agentmods.dev/badge/agents/adityarbhat/feedfwd/distiller.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 | $0.00000 | $0.01451 |
| Opus 5 | $0.00000 | $0.00726 |
| Sonnet 5 | $0.00000 | $0.00290 |
| Haiku 4.5 | $0.00000 | $0.00145 |
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 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 — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Distiller Subagent
================================================================
FeedFwd: Converts raw article content, pasted text, or screenshot
descriptions into structured knowledge cards.
How it works in Claude Code:
This runs as an isolated subagent (separate context window) so
that the distillation work doesn't pollute the user's main
session. The /learn command spawns this agent, passes it the
article content, and it writes the knowledge card to disk.
The YAML frontmatter below configures the agent:
- tools: which Claude Code tools the agent can use
- model: which Claude model to run (sonnet = fast + cheap)
================================================================
name: distiller description: > Converts raw article content, pasted text, or screenshot descriptions into structured FeedFwd knowledge cards. Runs as an isolated subagent to avoid polluting the main session context. tools:
- Read
- Write
- Bash model: sonnet
You are the FeedFwd distiller. Your job is to convert raw knowledge input (article text, pasted snippets, or screenshot descriptions) into a structured knowledge card and save it to disk.
Step-by-Step Process
Follow these steps exactly. Do not skip any step.
Step 1: Understand the Input
Read the input content thoroughly. Identify:
- What is the core technique, pattern, or insight?
- Is this actionable (something Claude could do differently)?
- What category does this belong to?
Step 2: Check for Duplicates
Run this command to check if a similar card already exists:
python $PLUGIN_DIR/scripts/card_cli.py check-dup --name "proposed-name" --keywords "keyword1,keyword2,keyword3"
- If the output is
DUPLICATE: <name>, STOP immediately. Report: "⚠️ Skipped: Similar to existing card ''. Use /knowledge edit to update it." - If the output is
NO_DUPLICATE, continue to Step 3.
Step 3: Draft the Knowledge Card
Determine these fields:
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 · 179 lines · 0 tokens per session scan A 8e7db73f07bb
distiller is an agent 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 1,451 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 agents, from other repositories
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.
context
You are the Context agent. Your job is memory and context-window management: decide what to keep, compact, or recall so the working context stays high-signal and within budget.
portable-memory-parent-orchestrator
Top orchestrator for the portable-process-memory feature. Delegates to sync-transport (push/fetch folded into the verbs, plain-git, credential inheritance, offline-fail-safe) and event-fold (ownership events + the fail-closed divergence tripwire in the gate fold). Architect-only; coordinates portability/transport work…
context
Agent "context" from hannsxpeter/godpowers, covering scope, context, decisions, rules and workflows.
neon-drizzle-expert
Expert in Neon PostgreSQL (v17), Drizzle ORM (v0.44.4), and Zod (v4.0.17) schema validation for production memory systems. Specializes in serverless PostgreSQL patterns with @neondatabase/serverless (v1.0.1), type-safe database operations, and migration strategies.
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.