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/llama-farm/llamafarm/founder_modegit clone --depth 1 https://github.com/llama-farm/llamafarmWhat 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 | $0.00169 |
| Opus 5 | $0.00000 | $0.00084 |
| Sonnet 5 | $0.00000 | $0.00034 |
| Haiku 4.5 | $0.00000 | $0.00017 |
Grade A, and why
founder_mode 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.
What it actually says
you're working on an experimental feature that didn't get the proper ticketing and pr stuff set up.
assuming you just made a commit, here are the next steps:
get the sha of the commit you just made (if you didn't make one, read .agents/commands/commit.md and make one)
read .agents/commands/github_issues.md - think deeply about what you just implemented, then create a github issue about what you just did - it should have ### headers for "problem to solve" and "proposed solution"
fetch the issue to get the recommended git branch name
git checkout main
git checkout -b 'BRANCHNAME'
git cherry-pick 'COMMITHASH'
git push -u origin 'BRANCHNAME'
gh pr create --fill
read '.agents/commands/describe_pr.md' and follow the instructions
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 · 21 lines · 0 tokens per session scan A 658591e23fbe
founder_mode is a command published in the GitHub repository llama-farm/llamafarm (837 stars, last pushed 2mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 169 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 2026-08-30.
Other commands, from other repositories
sync-go-engine
Synchronize the Go side — the engine runtime — with the current contract/workflow.yaml. The TypeScript side has its own sync command (/sync-ts-domain); this one does not touch ts/. Use this after the contract YAML has been edited (or pulled in from fh-backend) to add/remove/change nodes or their argument shapes.
sync-ts-domain
Synchronize the TypeScript side — workflow-core domain layer (and any workflow-builder knock-on edits) — with the current contract/workflow.yaml. The Go engine side has its own sync command; this one does not touch go/. Use this after the contract YAML has been edited (or pulled in from fh-backend) to…
audit
Perform a thorough audit of the React canvas in ts/workflow-builder/src/ against five categories. Use Agent subagents to explore categories in parallel where possible.
new-node
Author a new workflow node end-to-end — interview intent, design the contract schema, then reconcile both the TS and Go sides.
sync-translations
Audit the i18n trees for translation completeness across all locales. The hard, error-prone part — which node/param/edge/channel/memory/model descriptions still lack translations — is derived deterministically by a script; the rest are agent checks.
model-check
Reassess the current session and recommend the right model and effort level.