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/lool-ventures/founder-skills/feedbackgit clone --depth 1 https://github.com/lool-ventures/founder-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/commands/lool-ventures/founder-skills/feedback)<a href="https://agentmods.dev/commands/lool-ventures/founder-skills/feedback"><img src="https://agentmods.dev/badge/commands/lool-ventures/founder-skills/feedback.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 | $0.00041 | $0.00703 |
| Opus 5 | $0.00020 | $0.00351 |
| Sonnet 5 | $0.00008 | $0.00141 |
| Haiku 4.5 | $0.00004 | $0.00070 |
Grade A, and why
feedback 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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Send founder-skills feedback
Help the user send feedback to the founder-skills maintainers (lool ventures). You never transmit anything. You draft a message and hand the user a link/text; they submit it themselves via their own browser or mail client.
Privacy hard-stop (non-negotiable)
- NEVER put session or artifact data in the draft: no company name, cap-table numbers, deck content, financials, valuations, or transcript excerpts.
- NEVER include file paths — they leak company slugs (e.g.
artifacts/acme-corp/...). - You MAY include, only after showing the user the exact final text: plugin version
(read
${CLAUDE_PLUGIN_ROOT}/.claude-plugin/plugin.json), skill name, platform (Claude Code vs Cowork), and error class if it's a bug. Nothing else. - Show the complete payload and get an explicit "yes, send this" BEFORE producing any link.
Flow
-
Classify with AskUserQuestion (one question, these options): Bug · Idea or feedback · Question / help · Share a win
-
Gather briefly (1–3 prompts): which skill, what happened / what you'd want.
-
Draft + scrub a clean body per the hard-stop above. Show it in full for review/edit.
-
Offer private delivery: ask if they'd rather send it privately by email instead of posting publicly. If yes, use the mailto route below.
-
Produce the submit link (do not open or send it — the user clicks it):
Type Link Bug https://github.com/lool-ventures/founder-skills/issues/new?template=bug_report.md&title=<enc>&labels=bugIdea / feedback https://github.com/lool-ventures/founder-skills/discussions/new?category=ideas-feedbackQuestion / help https://github.com/lool-ventures/founder-skills/discussions/new?category=q-a-help-how-toShare a win https://github.com/lool-ventures/founder-skills/discussions/new?category=show-and-tell-founder-winsPrivate (any type) mailto:[email protected]?subject=<enc>&body=<enc>- URL-encode
<enc>values (spaces, newlines,#,&). - Discussions links don't reliably prefill the body — paste the drafted text into the thread after it opens. Issue and mailto links do prefill.
- If a prefilled URL would exceed ~6KB (GitHub) or ~1.5KB (mailto), skip the prefill and present the drafted text for the user to paste.
- URL-encode
-
Confirm: tell them to review on the opened page and submit. Thank them. If they shared a win, mention it may help other founders.
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 · 47 lines · 41 tokens per session scan A 856c098f18a8
feedback is a command published in the GitHub repository lool-ventures/founder-skills (32 stars, last pushed 3d ago), licensed Apache-2.0. It adds 41 tokens to every session and 703 once invoked, about $0.0002 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 2026-08-30.
Other commands, from other repositories
engage.actions
Execute Phase 7 - Actions on Objectives and Goal Achievement.
claude-tracker
List and browse your saved Claude Code sessions with status (running/inactive/VS Code).
update-workflow
Regenerate an existing custom workflow's shortcut command wiring from the current swarm template.
INDEX
16 custom slash commands in /.claude/commands/.
save
Save this conversation as a new or existing reusable context.
tidy
Consistency check for non-code repos with INDEX.md hierarchy. Verifies INDEX.md accuracy, MEMORY.md references, orphaned files, stale dates, and WAITING markers.