Borrowing it
Nothing to install: this file belongs to rjwalters/kicad-tools. 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/rjwalters/kicad-tools/main/.claude/commands/repo/followups.mdgit clone --depth 1 https://github.com/rjwalters/kicad-toolsWrote 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/rjwalters/kicad-tools/followups)<a href="https://agentmods.dev/commands/rjwalters/kicad-tools/followups"><img src="https://agentmods.dev/badge/commands/rjwalters/kicad-tools/followups/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/rjwalters/kicad-tools/followups"><img src="https://agentmods.dev/badge/commands/rjwalters/kicad-tools/followups.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 | $0.00031 | $0.06728 |
| Opus 5 | $0.00015 | $0.03364 |
| Sonnet 5 | $0.00006 | $0.01346 |
| Haiku 4.5 | $0.00003 | $0.00673 |
Grade A, and why
followups 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 9d 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 — 497 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/repo:followups — File Session Follow-Ups
Mine the current working session for follow-on work that was surfaced but not done — bugs found-but-not-fixed, deferred TODOs, documentation gaps, and limitations discovered in an upstream tool while using it — then file each as an issue in the right repo (this repo, or an upstream tool repo like Loom / Anvil / Repo Skills / kicad-tools).
Unlike every other /repo:* command, which scans repo / git / filesystem
state, this one mines the conversation: the deferred work and discovered
bugs that only exist in the session's context. Filing is outward-facing — for
upstream targets it writes into other people's repos, usually public ones —
so this command is in the same "always confirm first" class as release,
remote, and update-tools, never the auto-apply behavior of the hygiene
commands. Confirmation is the default and only mode; there is no --ask flag
because there is nothing to opt into.
Mining a private session and publishing into a public repo is a visibility boundary crossing, so every cross-repo candidate is scrubbed at authoring time against [[scrub]]'s detection classes before it is ever proposed — see step 3b.
Usage
/repo:followups # Review this session, propose issues, confirm, then file
/repo:followups --dry-run # Propose only — show what would be filed, file nothing
/repo:followups --repo loom # Restrict to follow-ups targeting one tool repo
/repo:followups --here # Only this repo; skip all upstream tool repos
Steps
1. Mine the session for candidates
Review the working session and collect concrete follow-on work in four categories. Only include work that was actually surfaced — do not invent tasks.
- Bugs found but not fixed — something broke or misbehaved and was noted but left unaddressed (in this repo's code or in a tool being used).
- Deferred TODOs — "we should do X later", "out of scope for now", intentionally punted work.
- Documentation gaps — missing/stale/wrong docs noticed while working.
- Upstream tool limitations — a bug, missing feature, or rough edge in an installed tool (Loom, Anvil, Repo Skills, kicad-tools) hit while using it.
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.
- 9d ago First seen · 497 lines · 31 tokens per session scan A c02d911c4fcc
followups is a command published in the GitHub repository rjwalters/kicad-tools (56 stars, last pushed today), licensed MIT. It adds 31 tokens to every session and 6,728 once invoked, about $0.0002 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 2026-08-30.
Other commands, from other repositories
template
Manage issue templates for streamlined issue creation.
sync-linear
Sync current work with Linear ticket status.
add-note
Add an internal or external note to a ConnectWise PSA ticket.
fest-show
Show festival progression (in-progress tasks, roadmap, and dependency view).
dispatcher
Pick the next-best repo to work on across the portfolio — rank free repos, recommend one, claim its lease atomically, and route to the entry command.
workpm
A project-management workflow for coordinating multiple AI workers through five stages. It includes task assignment, shared activity logs, worker replacement, and final checks.