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/dreamgit 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 | $0.00064 | $0.01605 |
| Opus 5 | $0.00032 | $0.00803 |
| Sonnet 5 | $0.00013 | $0.00321 |
| Haiku 4.5 | $0.00006 | $0.00161 |
Grade A, and why
dream 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dream
Process all unprocessed rants in brain/rants/. Distil what surfaced. Write a tight 5-line digest. Hard cap on output. The user will not read more than 5 lines.
Procedure
-
Walk
brain/rants/. For each file, parse entries by frontmatter. Collect every entry whereprocessed: false. -
For each unprocessed entry, classify what it contains and stamp every new entry with a stable ID per
rules/entry-conventions.md:- Pattern - recurring theme, observation, framework. Append to
brain/patterns.mdwith a stampedpattern-YYYY-MM-DD-NNNID. - Flag - stall, frustration, role feedback, friction. Append to
brain/flags.mdwithStatus: **OPEN.**and Severity Week 1 unless escalation is obvious. Stampflag-YYYY-MM-DD-NNN. - Parked decision - idea waiting for a trigger. Append to
brain/decisions-parked.mdwith a Trigger to revisit line. Stampparked-YYYY-MM-DD-NNN. - Need / blocker - something the user must do or decide. Add or update a row in
brain/needs-input.md(Specific + Impact columns). Stampneed-YYYY-MM-DD-NNNon new entries. - Preference - the user said something about how they want to be worked with, not about the business. "Stop giving me three options." "I hate being asked twice." "Just tell me what you think." Append a row to the Proposed table in
core/working-preferences.md- never the Active table - with the preference in their words, where it applies, today's date, and the quote as evidence. Stamppref-YYYY-MM-DD-NNN. If the file does not exist, copy it fromtemplates/working-preferences.mdfirst. - Client signal - mention of a named person or company that warrants tracking. Update
context/clients.md. - Log only - context, no action needed. Skip; the rant file itself is the record.
For each channel: read the target file, find the highest existing
<channel>-<today>-<NNN>, increment by 1, zero-pad to 3 digits. Track the IDs you stamp. You will cite them in the digest. - Pattern - recurring theme, observation, framework. Append to
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 · 73 lines · 64 tokens per session scan A 72d6af67f57d
dream is a command published in the GitHub repository ARCASSystems/FounderOS (5 stars, last pushed 18d ago), licensed MIT. It adds 64 tokens to every session and 1,605 once invoked, about $0.0003 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.