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.
git clone --depth 1 https://github.com/damusix/atomic-claudeWrote 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/damusix/atomic-claude/follow-up)<a href="https://agentmods.dev/commands/damusix/atomic-claude/follow-up"><img src="https://agentmods.dev/badge/commands/damusix/atomic-claude/follow-up.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 5.1 | $0.00000 | $0.04211 |
| Opus 5 | $0.00000 | $0.02106 |
| Sonnet 5 | $0.00000 | $0.00842 |
| Haiku 4.5 | $0.00000 | $0.00421 |
Grade A, and why
follow-up 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 7d 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 — 383 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Handle pending reminders and project follow-up entries. Three modes: bare (/follow-up), cron-fired (/follow-up due <id>), and review (/follow-up review).
Spec: docs/spec/cron-workflow.md § /follow-up
<reminders-dir> below is atomic where --json's reminders field when the atomic binary is present, else the .claude/.scratchpad/reminders/ fallback dir used when it is absent — the legacy path reminder.List already unions and atomic migrate already relocates. Paths come from atomic scratchpad / atomic where --json; if what you find on disk does not match, run atomic migrate --show-log for the change history.
Mode detection
Inspect $ARGUMENTS:
- Empty → bare flow (interactive list, steps 1–6 below).
due <id>→ cron-fired flow (steps A–D below).review→ review flow (steps R1–R6 below).
Bare flow
Step 1 — Build the indexed reminder list
Detect binary:
-
Binary present (
command -v atomicexits 0):atomic reminder listOutput is indexed and includes the
transportcolumn. Capture it. -
Fallback (binary absent): list and parse files manually:
ls .claude/.scratchpad/reminders/*.md 2>/dev/nullFor each file, extract frontmatter fields via grep:
grep -m1 '^id:' <file> # → id grep -m1 '^created:' <file> # → created timestamp grep -m1 '^transport:' <file> # → transport (cron|routine|none)Then read the body (lines after the closing
---). Build an indexed list from those fields.If no files found: print
no reminders.and exit.
Step 2 — Optionally enrich with schedule info
For each reminder, attempt to find its live schedule entry:
crontransport: callCronListand search for an entry whose prompt contains/follow-up due <id>. If found, note the next-fire time as "fires in X" or "fires at ".routinetransport: if a routine listing is accessible, search for an entry with the matching prompt. Note fire time if found.nonetransport: no schedule lookup needed. The reminder will surface via the session-start hook only.
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.
- 7d ago First seen · 383 lines · 0 tokens per session scan A ee40c28085b3
follow-up is a command published in the GitHub repository damusix/atomic-claude (84 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 4,211 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 2026-08-30.
Other commands, from other repositories
handoff
Shift change: brief successor on context, workflow, pending work, and verification commands.
add-agent
Add a new sub-agent to the current plugin for specialized tasks.
add-skill
Add a new Skill to the current plugin with proper structure.
add-command
Add a new slash command to the current plugin.
maintain-check
Run one durable maintainer autopilot cycle — budget-gated, stop-guarded, checkpointed. Use --dry-run to preview without executing.
dream
Overnight autoresearch + maintainer sweep that surfaces a MORNING REPORT — suggested changes, issues raised with fixes, and kept improvements. Shadow-first; never auto-pushes. Runs on-demand or scheduled for off-hours.