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/arcassystems/founderos/log-replygit clone --depth 1 https://github.com/ARCASSystems/FounderOSWhat 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 | $0.00094 | $0.00783 |
| Opus 5 | $0.00047 | $0.00392 |
| Sonnet 5 | $0.00019 | $0.00157 |
| Haiku 4.5 | $0.00009 | $0.00078 |
Grade A, and why
log-reply 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 2d 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 — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Log reply
Run the log-reply skill at skills/log-reply/SKILL.md end to end.
Procedure
- If
core/identity.mddoes not exist, replyFounder OS not set up here. Say "set up Founder OS" first.and stop. - If
skills/log-reply/SKILL.mdis missing, replylog-reply skill not found at skills/log-reply/SKILL.md. Restarting Claude Code fixes this most of the time, because it reloads what is installed. If it happens again after a restart, say "update Founder OS".and stop. - If
brain/log.mdis missing, replybrain/log.md missing. Say "set up Founder OS" to build it.and stop. - Follow the log-reply skill instructions exactly. The thread body (and source label, if provided) is whatever follows the command, or what the operator pastes when prompted in Step 1.
- Write the structured entry to
brain/log.mddirectly (auto-runnable). - Surface proposed updates to
context/clients.mdandcontext/leads.md. Wait for the operator's yes perrules/approval-gates.mdbefore any of those edits land. - Output the under-120-word confirmation block defined in the skill.
When to use
- A reply landed and you want it on disk and cross-referenced before you forget the context.
- A long WhatsApp or Telegram thread surfaced new commitments and you want them tracked.
- An email exchange with multiple turns needs to be condensed into one log entry per conversation.
- A voice memo transcript captures a phone call you took.
When NOT to use
- You ran a meeting and have a transcript. Use
/founder-os:capture-meeting <name>instead. - You want to log a free-form thought, not a thread reply. Use
/founder-os:rantor the brain-log skill directly. - You want to draft a reply. Use the email-drafter skill.
Examples
/founder-os:log-replythen paste the WhatsApp export when prompted./founder-os:log-replythen paste the email body and label it asemail.- "I got a reply from Sam, log this thread" - the natural-language trigger fires the same skill.
Rules
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.
- 2d ago First seen · 48 lines · 94 tokens per session scan A b0956690d7d3
log-reply is a command published in the GitHub repository ARCASSystems/FounderOS (5 stars, last pushed 18d ago), licensed MIT. It adds 94 tokens to every session and 783 once invoked, about $0.0005 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 2026-08-31.
Other commands, from other repositories
wiki-query
Ask questions against the wiki. Synthesizes answers from wiki pages with cross-reference citations.
wiki-digest
Generate a daily or weekly digest of wiki changes — new sources, pages, insights, and gaps.
demo-command
Example slash command that wraps the demo-skill. Showcases the command kind.
ingest-l1
L1 analysis loop for the abapwiki knowledge base: for each batch it launches the abap-analyzer sub-agent in parallel, then the adversarial judge abap-deepcheck (separate session), applies only the analyses that pass the fail-closed gate, and commits. Resumes exactly after an interruption. Use this skill to document…
web-search
Search fetched web-source Markdown by regex and pull surrounding context for the best hits. Optionally restrict to one source alias.
docs-refresh
Re-fetch a cached source, ignoring the 7-day cache. Use when upstream content has changed.