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 skills add OdinMB/ops-workflow --skill review-followupgit clone --depth 1 https://github.com/OdinMB/ops-workflowWrote 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/skills/odinmb/ops-workflow/review-followup)<a href="https://agentmods.dev/skills/odinmb/ops-workflow/review-followup"><img src="https://agentmods.dev/badge/skills/odinmb/ops-workflow/review-followup/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/skills/odinmb/ops-workflow/review-followup"><img src="https://agentmods.dev/badge/skills/odinmb/ops-workflow/review-followup.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 | $0.00039 | $0.01361 |
| Opus 5 | $0.00019 | $0.00681 |
| Sonnet 5 | $0.00008 | $0.00272 |
| Haiku 4.5 | $0.00004 | $0.00136 |
Grade A, and why
review-followup 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review Follow-Up
Process follow-up .md files left by autonomous commands (/ops:batch-execute, /ops:get-to-work).
1. Find the follow-up file
If $ARGUMENTS contains a file path, use that. Otherwise, search for follow-up files:
- Check
.plans/andplans/for files matching*follow*up*or*followup*. - If multiple found, list them and ask the user which to review.
- If none found, tell the user and stop.
Read the file. Also read the branch's git log (git log main..HEAD --oneline) to understand what was done.
2. Frame what's open
Triage first (see Rules), then open with two or three sentences: what the run produced, and what kinds of decisions are still waiting on the user. If whoever invoked this skill has already said what the run produced — the /ops:get-to-work handoff does — don't say it again; open with what's still open. No item count, no section-by-section inventory, no commit count — the branch and its log are yours to keep track of.
3. Walk through each section
Decidable before asked. Never ask "what do you want to do about X?" without first making X decidable — at the level the user decides at. Read the plan file, the artifact, the state file, run git show on the commit, whatever it takes so you understand the concrete reality. Then say it in plain terms: what the project has now, what's wrong or thin about it, what each option would change, and what it costs. Don't paste what you read. Quote a document only when the text itself is the thing being decided — copy the user will send, an answer to a form, a spec — or when they ask.
Process sections in this order (skip empty ones):
Implementation Issues
These block quality. Present each issue with options:
- Fix now — address the issue immediately
- Create backlog item — add to
.plans/orbacklog/for later - Dismiss — not worth fixing
Controversial Decisions
The agent made a judgment call. For each, say what it chose and why in terms of what the deliverable now claims or does — not the edits it made — then offer:
- Keep as-is — the agent's choice is fine
- Revert — undo this specific change (identify the commit)
- Modify — adjust the approach (ask what they want)
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 · 89 lines · 39 tokens per session scan A a947832bdb02
review-followup is a skill published in the GitHub repository OdinMB/ops-workflow (7 stars, last pushed 22d ago), licensed MIT. It adds 39 tokens to every session and 1,361 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 2026-08-31.
Other skills, from other repositories
dev-finish
Close out a session — summarise what changed, capture what was learned, and prepare the commit.
dev-cycle
Run a feature end to end — scout the code, plan it, build it, and keep a session file so a closed terminal doesn't lose the thread.
factory-close
Close out a Linear issue — move to Done, add a closing comment, and clean up the local branch/worktree.
factory-setup-linear
Configure portable Linear workflow settings in .factory-kit/linear.json, migrating legacy .claude/linear.json settings when present.
factory-submit
Move the current branch's Linear issue to "In Review".
synergy-tracker
Manage cross-project synergy tracking between sibling projects. Use when the user wants to log a shared pattern, a divergence, an extraction candidate, or something a sibling project has that this one doesn't. Also use when the user wants to promote synergy entries to Basic Memory (workflow 5). NOT for upstream…