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/regen-coordination/org-os-template/initializegit clone --depth 1 https://github.com/regen-coordination/org-os-templateWhat 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 | $0.00015 | $0.00568 |
| Opus 5 | $0.00008 | $0.00284 |
| Sonnet 5 | $0.00003 | $0.00114 |
| Haiku 4.5 | $0.00002 | $0.00057 |
Grade A, and why
initialize scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are opening a new org-os session. Follow these steps exactly.
Step 1: Sync
Pull latest changes (skip silently if offline or no remote):
TOPLEVEL=$(git rev-parse --show-toplevel 2>/dev/null)
if [ "$TOPLEVEL" = "$(pwd)" ]; then
git pull --rebase --quiet 2>&1 || echo "sync: no remote or offline — continuing with local state"
else
echo "sync: embedded repo — skipping pull"
fi
Step 2: Render Dashboard
Run the initialize script with --format=markdown and print its output verbatim — the script renders the full ASCII dashboard. Do not reformat, re-render, or wrap in extra markdown:
node scripts/initialize.mjs --format=markdown
If the script fails (missing deps, node not found):
- Try
npm install, then retry once. - If still failing, fall back to reading these files directly and produce a minimal status summary:
IDENTITY.md,HEARTBEAT.md,federation.yaml,data/projects.yaml,data/tasks.yaml, recent files inmemory/, anddocs/agent-plans/QUEUE.md. - Never block — always produce something useful.
Step 2b: Buzz channel read-back (optional, fail-open)
If the workspace has the Buzz lane configured (npm run buzz:doctor exits 0), run
npm run buzz:read and include its output block in the session context under
"Since last session". If the doctor is not green, skip silently — one line at most.
Step 3: Note Session Context
Silently note for the rest of the session:
- Organization (from header /
federation.yaml) - Highest-priority task (Critical / Urgent in the dashboard)
- Active projects and active plans (from Plans / Pipelines section)
- Funding deadlines within 30 days
- What was worked on last (Recent Context)
Step 4: Wait for the Operator
End by displaying the Session Prompt with 3 contextual suggestions (already produced by the script), then wait for the operator to pick what to work on. Transition to Phase 2: PLAN — load context, analyze, present a tight 5–7 step work plan, then execute.
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 · 57 lines · 15 tokens per session scan A 43725f6b9e12
initialize is a command published in the GitHub repository regen-coordination/org-os-template (5 stars, last pushed 3d ago), licensed MIT. It adds 15 tokens to every session and 568 once invoked, about $0.0001 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
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.