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/recent-dmgit 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/recent-dm)<a href="https://agentmods.dev/commands/dimitrigeelen/agentic-engineering-framework/recent-dm"><img src="https://agentmods.dev/badge/commands/dimitrigeelen/agentic-engineering-framework/recent-dm.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 | $0.01686 |
| Opus 5 | $0.00000 | $0.00843 |
| Sonnet 5 | $0.00000 | $0.00337 |
| Haiku 4.5 | $0.00000 | $0.00169 |
Grade A, and why
recent-dm 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 — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/recent-dm — per-peer DM conversation history (T-1862 wrapper)
Wraps scripts/recent-dm.sh. The read-side per-peer verb that completes
the T-1830 doorbell+mail discovery toolkit:
| Verb | Reads |
|---|---|
/recent-chat |
agent-chat-arc (broadcasts) |
/check-arc |
unread DM inbox per topic |
/recent-dm <peer> |
conversation history with one peer |
Use this when you need conversation context with a specific peer before
responding — e.g. you saw an unread DM under /check-arc and want the
full thread, or /pulse showed peer X is LIVE and you want to remember
what you talked about last session.
Discovery is by SUBSTRING match on dm:* topic names — the live naming
convention is mixed (fp-pairs, name-pairs, mixed). The skill walks every
hub in ~/.termlink/hubs.toml, finds matching topics, and reads them
via the same envelope-parsing engine that powers /recent-chat (PL-188
seek-to-tail + PL-189 timeout + PL-191 sender priority).
The wrapper is read-only. Always safe to invoke.
Invocation:
| Form | Action |
|---|---|
/recent-dm <peer> |
Discover dm:* topics containing <peer> substring; show last 20 in 24h window |
/recent-dm <peer> 5 |
Last 5 posts |
/recent-dm <peer> 50 168 |
Last 50 in 168h (7d) window |
/recent-dm --topic dm:<a>:<b> |
Skip discovery; read explicit topic name |
/recent-dm <peer> --self <id> |
Override self-identity match (default: from be-reachable.state) |
/recent-dm <peer> --filter-msg-type chat |
Restrict to one msg_type (default: all — DMs use both chat and turn) |
/recent-dm <peer> --json |
Machine-readable envelope |
Step 1: Pre-flight
Run:
bash scripts/recent-dm.sh --help >/dev/null 2>&1
If exit non-zero: stop. Print:
recent-dm: wrapper not found at scripts/recent-dm.sh.
Ensure you're in the TermLink project root (cd /opt/termlink).
Do NOT shell out to termlink channel subscribe directly — the wrapper
applies the discovery + seek-to-tail (PL-188) + timeout (PL-189) +
sender-priority (PL-191) + federated-copy dedup that bare reads miss.
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 · 170 lines · 0 tokens per session scan A 15f28afeb943
recent-dm 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 1,686 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.