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/handoffgit clone --depth 1 https://github.com/regen-coordination/org-os-templateWrote 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/regen-coordination/org-os-template/handoff)<a href="https://agentmods.dev/commands/regen-coordination/org-os-template/handoff"><img src="https://agentmods.dev/badge/commands/regen-coordination/org-os-template/handoff.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 | $0.00061 | $0.00716 |
| Opus 5 | $0.00030 | $0.00358 |
| Sonnet 5 | $0.00012 | $0.00143 |
| Haiku 4.5 | $0.00006 | $0.00072 |
Grade A, and why
handoff 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 5d 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 — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are generating a handoff prompt — a compact, copy-paste brief another operator pastes into THEIR clone of this org-os instance (any agent/editor) to pick up a piece of work. It self-syncs their trunk with plain git (no dependency on /sync existing), points them at the target, and ends with a clean trunk→main PR.
The output is the deliverable. Keep it minimal.
Step 1: Parse the ask
$ARGUMENTS = <operator> <target> [the ask…]
- operator → trunk: resolve the operator's trunk slug from the instance's operator roster (
data/members.yaml, or the trunk branches on the remote:git branch -r). If ambiguous, ask which trunk. - target: a repo doc (
docs/SOME-DOC.mdor a bare filename, optionally a§N/heading) or a task id (task-…, resolve fromdata/tasks.yaml). - the ask: the rest — one clause naming the concrete deliverable. If absent, infer from the target; if still unclear, ask ONE question. Don't over-ask.
Step 2: Resolve link + trunk
- Live link: derive the repo's web URL from
git remote get-url origin→https://github.com/<org>/<repo>/blob/main/<docpath>(append#<anchor>only if confident it resolves; otherwise name the section inside the ask). For a task, link the same repo path todata/tasks.yamland cite the id. - Confirm the trunk slug from Step 1.
Step 3: Emit the prompt (a single paragraph the operator pastes into their instance)
The prompt is an instruction to THEIR agent (Claude Code / OpenCode / Cursor / Zed) — natural language; the agent does the git sync, the edits, and the PR. Output ONLY this filled template in a code block, nothing else:
In <REPO-NAME>: sync my `<TRUNK>` trunk with `main` — fetch, switch to <TRUNK>, merge `origin/main` (fast-forward if possible, else a merge commit), push. Then open <LINK> and <ASK>. Commit to <TRUNK> and open a PR to `main`.
Rules:
- One paragraph, no shell fences — the agent decides the exact commands.
<ASK>= section (§N) + the concrete deliverable, one clause.- If the target operator's trunk is far-behind/messy (e.g. a committed venv), extend the sync clause in-line:
(if it conflicts, keep origin/main for shared files; if a venv is tracked, untrack it + gitignore).
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.
- 5d ago First seen · 37 lines · 61 tokens per session scan A 09b54152d456
handoff is a command published in the GitHub repository regen-coordination/org-os-template (5 stars, last pushed 6d ago), licensed MIT. It adds 61 tokens to every session and 716 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
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.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.