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 commands/adityarbhat/feedfwd/knowledgegit clone --depth 1 https://github.com/adityarbhat/feedfwdWhat 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 | $0.00788 |
| Opus 5 | $0.00000 | $0.00394 |
| Sonnet 5 | $0.00000 | $0.00158 |
| Haiku 4.5 | $0.00000 | $0.00079 |
Grade A, and why
knowledge 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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/knowledge Command
================================================================
FeedFwd: Browse, search, and manage the knowledge base.
How it works in Claude Code:
When a user types "/knowledge [subcommand]", Claude Code reads
this file and follows the instructions. The heavy lifting is
done by card_cli.py — this command just runs it and formats
the output nicely for the user.
================================================================
name: knowledge description: "Browse, search, and manage your FeedFwd knowledge base" arguments: "[subcommand] [args]"
You are handling the FeedFwd /knowledge command. This provides a
management interface to the user's knowledge base.
Step 1: Determine the Subcommand
Look at the arguments the user provided:
| User types | Subcommand | Action |
|---|---|---|
/knowledge |
list | Show all cards grouped by category |
/knowledge search <term> |
search | Search across cards |
/knowledge show <name> |
show | Display a card's full content |
/knowledge edit <name> |
edit | Help user edit a card |
/knowledge remove <name> |
remove | Delete a card |
/knowledge stats |
stats | Show knowledge base statistics |
Subcommand: list (default)
Run this command and show the output directly to the user:
python scripts/card_cli.py list
The output is already formatted — just pass it through.
Subcommand: search
Run this command with the user's search term:
python scripts/card_cli.py search "<term>"
Show the results. If matches are found, ask if the user wants to see
the full content of any card (offer to run show).
Subcommand: show
Run this command with the card name:
python scripts/card_cli.py show "<name>"
Show the full output to the user. The output includes the card's insight, injection text, example, metadata, and file path.
Subcommand: edit
For editing a card, there are two approaches:
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 · 116 lines · 0 tokens per session scan A ec0d73c79136
knowledge is a command 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 788 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.