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/dimitrigeelen/agentic-engineering-framework/agent-handoffgit clone --depth 1 https://github.com/DimitriGeelen/agentic-engineering-frameworkWrote 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/dimitrigeelen/agentic-engineering-framework/agent-handoff)<a href="https://agentmods.dev/commands/dimitrigeelen/agentic-engineering-framework/agent-handoff"><img src="https://agentmods.dev/badge/commands/dimitrigeelen/agentic-engineering-framework/agent-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 | $0.00000 | $0.01589 |
| Opus 5 | $0.00000 | $0.00794 |
| Sonnet 5 | $0.00000 | $0.00318 |
| Haiku 4.5 | $0.00000 | $0.00159 |
Grade A, and why
agent-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 today.
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 — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/agent-handoff - Cross-Host Agent Contact (T-1429 wrapper)
Wraps termlink agent contact so vendored Claude Code agents can hand off
context to a peer agent in one command. Replaces the legacy remote push
- inbox.push improv pattern (T-1166 retired).
Invocation: /agent-handoff <target> <task-id> "<message>"
<target>— the peer agent's display_name, resolvable via localtermlink session.discover(e.g.,framework-agent,oss-dash).<task-id>— the active task this handoff belongs to (e.g.,T-1429). Must exist under.tasks/active/. Embedded as a[T-XXX]prefix in the message body so the receiver can route by thread.<message>— the handoff summary in plain text. Quote it.
Protocol canon is documented on the topic itself — run
termlink channel info agent-chat-arc to see the 5 invariants in-place
(T-1430).
Step 1: Verify the task exists
Run:
ls .tasks/active/<task-id>-*.md 2>/dev/null
If no match, stop. Print:
agent-handoff: task <task-id> not found in .tasks/active/.
Create it first: fw work-on "topic" --type build
Exit non-zero. Do NOT post to a non-existent task.
Step 2: Capture self identity (for log visibility)
Run:
termlink whoami --json 2>/dev/null
If single candidate: capture sender_id.
If multi-candidate (multiple sessions on this hub): prefer the one whose
cwd matches $(pwd). If still ambiguous, fall back to the first
candidate and note the ambiguity in the Update entry.
If whoami fails: continue with sender_id=unknown — identity binding
is enforced server-side once T-1427 ships, not here.
Step 3: Post to the peer
Run:
termlink agent contact "<target>" --message "[<task-id>] <message>" --json
Capture stdout. The actual JSON shape (T-1429 Phase-1, verified live 2026-05-01):
{
"delivered": { "offset": <integer>, "ts": <ms-since-epoch> }
}
If exit code is non-zero or delivered is missing: stop. Print the
verb's stderr and exit non-zero. The verb already prints actionable
errors (peer offline, missing identity_fingerprint, etc.) — do not
swallow them.
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.
- today First seen · 168 lines · 0 tokens per session scan A 1da1e6032642
agent-handoff is a command published in the GitHub repository DimitriGeelen/agentic-engineering-framework (13 stars, last pushed today), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,589 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 2026-09-04.
Other commands, from other repositories
service-check
Request each agent to run a self-diagnostic to validate their runtime setup.
compatibility-audit
Audit all agents for Trinity compatibility by requesting self-diagnostics from each agent.
request-research
Ask the researcher to investigate a specific topic.
health
Perform a health check on all agents and identify any issues.
schedules
Quick overview of all schedules across the platform.
status
Report on recent research activity and findings count.