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/since-last-sessiongit clone --depth 1 https://github.com/ARCASSystems/FounderOSWrote 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/arcassystems/founderos/since-last-session)<a href="https://agentmods.dev/commands/arcassystems/founderos/since-last-session"><img src="https://agentmods.dev/badge/commands/arcassystems/founderos/since-last-session.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 | $0.00000 | $0.00690 |
| Opus 5 | $0.00000 | $0.00345 |
| Sonnet 5 | $0.00000 | $0.00138 |
| Haiku 4.5 | $0.00000 | $0.00069 |
Grade A, and why
since-last-session 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 — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Founder OS since last session
Run the since-last-session skill at skills/since-last-session/SKILL.md end to end. No arguments.
Procedure
- If
core/identity.mddoes not exist, replyFounder OS not set up here. Say "set up Founder OS" first.and stop. - If
skills/since-last-session/SKILL.mdis missing, replysince-last-session skill not found at skills/since-last-session/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/does not exist, replybrain/ folder missing. Say "set up Founder OS" to build it.and stop. - Follow the since-last-session skill instructions exactly.
- If
brain/.last-sessionis missing: print the seed message, write the marker, stop. No delta on the first run. - If
brain/.last-sessionis present: read it, compute elapsed time, render the 5-section report, then overwrite the marker with the current ISO-8601 timestamp.
- If
- Output the structured block defined in the skill. Nothing before, nothing after the fenced block, except the one-line
Marker advanced to ...confirmation outside the fence.
When to use
- Returning to the OS after a gap and you want the delta, not the full read.
- Before any planning work, so the report scopes to what shifted while you were away.
- After a parallel session ran on another machine and you want a quick "what is new on disk".
When NOT to use
- Full state-of-the-OS orientation. Use
/founder-os:strategic-readfor the 5-section read across the brain. - A single-topic question. Use
/founder-os:brain-pass "<question>"or/founder-os:query "<keyword>".
Examples
/founder-os:since-last-session- "what changed since last session"
- "catch me up since I was last here"
Rules
- The skill reads the file layer and writes only to
brain/.last-session. No other file is modified. - No external dependencies. No paid API. Git is used only to list filenames; the skill runs without git if the install is not a repo.
- No em dashes or en dashes. Hyphens only with spaces.
- No banned words per
rules/writing-style.mdor its template fallback. - The five section headers are a contract. Keep them verbatim.
- First run seeds the marker only. Subsequent runs report the delta.
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 · 45 lines · 0 tokens per session scan A 891b8a2fd91a
since-last-session is a command published in the GitHub repository ARCASSystems/FounderOS (5 stars, last pushed 21d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 690 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
wiki-retro
Save an atomic insight from the current task into the wiki. Creates a single markdown file that layered recall surfaces in future sessions.
wiki-discover
Auto-discover new sources from the web. Searches based on config topics and known knowledge gaps.
wiki-init
Initialize a new LLM Wiki in the current directory. Creates the full directory structure, config, and template files.
wiki-run
Run the full wiki cycle: discover → ingest → lint. Optionally schedule for auto-updates.
wiki-lint
Health check the wiki. Detects contradictions, orphans, missing pages, stale claims, and knowledge gaps.
wiki-status
Show wiki health overview — source count, page stats, orphan count, last activity dates.