Borrowing it
Nothing to install: this file belongs to DimitriGeelen/agentic-engineering-framework. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/DimitriGeelen/agentic-engineering-framework/master/.claude/commands/recent-chat.mdgit 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-chat)<a href="https://agentmods.dev/commands/dimitrigeelen/agentic-engineering-framework/recent-chat"><img src="https://agentmods.dev/badge/commands/dimitrigeelen/agentic-engineering-framework/recent-chat/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/dimitrigeelen/agentic-engineering-framework/recent-chat"><img src="https://agentmods.dev/badge/commands/dimitrigeelen/agentic-engineering-framework/recent-chat.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00000 | $0.01447 |
| Opus 5.5 | $0.00000 | $0.00579 |
| Sonnet 5.5 | $0.00000 | $0.00289 |
| Haiku 4.5 | $0.00000 | $0.00145 |
Grade A, and why
recent-chat 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 1mo 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 — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/recent-chat — show recent agent-chat-arc posts across the fleet (T-1849 wrapper)
Wraps scripts/agent-chat-arc-recent.sh. The "what's been said?" verb in the
T-1830 doorbell+mail arc discovery triangle:
- Who's there? —
/be-reachable status+agent-listeners-fleet.sh - Is the rail healthy? —
termlink fleet doctor+check-fleet-doorbell-mail-health.sh - What's been said? — this skill
Use this when an agent landing in a fresh session wants conversation context
before responding. Pairs with /check-arc (your unread DMs) and
/agent-handoff (initiate a fresh thread).
Invocation:
| Form | Action |
|---|---|
/recent-chat |
Last 20 posts in 24h window, fleet-wide |
/recent-chat 5 |
Last 5 posts |
/recent-chat 50 168 |
Last 50 posts in 168h (7d) window |
/recent-chat --since N |
Specific window in hours (1..720) |
/recent-chat --limit N |
Specific post count (1..200) |
/recent-chat --hub addr |
Single-hub mode |
/recent-chat --filter-sender ID |
Posts from one specific sender |
/recent-chat --all-msg-types |
Include heartbeats / receipts (not just chat) |
/recent-chat --exclude-heartbeats |
Exclude *-vendored systemd emitter posts; surface real conversation only (T-1861). Header reports excluded counts |
/recent-chat --json |
Machine-readable envelope |
The wrapper is read-only. Always safe to invoke.
Step 1: Pre-flight
Run:
bash scripts/agent-chat-arc-recent.sh --help >/dev/null 2>&1
If exit non-zero: stop. Print:
recent-chat: wrapper not found at scripts/agent-chat-arc-recent.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 seek-to-tail (PL-188) + timeout (PL-189) + sender-priority
(PL-191) corrections that bare reads miss.
Step 2: Parse arguments
$ARGUMENTS is the user's tail. Normalize:
- If
$ARGUMENTSis empty → run with no args (defaults: limit=20, since=24). - If
$ARGUMENTSstarts with a positive integer N → first integer is--limit N. - If a second positive integer follows → second integer is
--since N. - Any token starting with
--is passed through verbatim.
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.
- 1mo ago First seen · 153 lines · 0 tokens per session scan A 57ff99873ca5
recent-chat is a command published in the GitHub repository DimitriGeelen/agentic-engineering-framework (18 stars, last pushed yesterday), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,447 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
list
List recent task executions across all agents.
pause
Pause one or more schedules to temporarily stop automated executions.
pull-learnings
Pulls shared organization patterns into local org-patterns.toon.
usually
Prompt Pocket — list your high-frequency prompts and pick one to run; manage your go-to prompts with add/delete/edit/find. Generates a native slash dropdown so you can pick a saved prompt directly.
dashboard-session-list
List all pi sessions (id, status, name, cwd). Runs locally, no LLM.
vitaecontext-vitaegraph
Create, validate, index, or use a private VitaeGraph.