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 theam/claude-dev-kit --skill follow-upsgit clone --depth 1 https://github.com/theam/claude-dev-kitWrote 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/theam/claude-dev-kit/follow-ups)<a href="https://agentmods.dev/skills/theam/claude-dev-kit/follow-ups"><img src="https://agentmods.dev/badge/skills/theam/claude-dev-kit/follow-ups/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/theam/claude-dev-kit/follow-ups"><img src="https://agentmods.dev/badge/skills/theam/claude-dev-kit/follow-ups.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 | $0.00080 | $0.00917 |
| Opus 5 | $0.00040 | $0.00458 |
| Sonnet 5 | $0.00016 | $0.00183 |
| Haiku 4.5 | $0.00008 | $0.00092 |
Grade A, and why
follow-ups 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 6d 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Follow-ups
Close the loop: when a story finishes, the loose ends it surfaced should be tracked, not just described in the PR body. This skill turns them into real work items in the configured tracker, linked back to the source story — created only after approval. It's the tracking counterpart to the "Out of scope / follow-ups" section create-pr already writes.
Preconditions
.claude/dev-kit.jsonexists with atrackerblock (otherwise rundev-kit-setupfirst).- The adapter's backend is authenticated (MCP connector authorized, or
gh/azlogged in) — otherwise tell the user how to authenticate and stop. - The source story key (the item just delivered) is known, for linking. If unknown, ask once.
1. Gather the loose ends — only real ones
Collect follow-ups from the story just finished, from where they were already surfaced:
- the "Out of scope / follow-ups" list in the
create-prPR body, - deferred review findings from
fix-pr/pr-review(the "defer to a tracked issue" bucket), - deliberate TODOs / known gaps the implementation left.
Never invent follow-ups. If there are none, say so and stop — don't pad a backlog to look thorough.
2. Propose — WAIT FOR APPROVAL
For each loose end, propose a work item:
- Type: default Task; use a User Story when it's a user-facing increment (ask if unsure).
- Title + a one-line description + why (the context from the story that produced it).
- Link to the source story (and its epic/parent when there is one) for traceability.
- A sizing hint or label when the team uses them (discover, don't assume).
Present the full list and wait for explicit approval; the user may edit or drop items. Create nothing until approved.
3. Create — via the tracker's write adapter
Create each approved item and link it to the source story. Verify writes by read-back where the CLI can silently no-op.
Jira (type: "jira") — Atlassian MCP
createJiraIssue for each item (project, type, summary, description, labels); link to the source with createIssueLink ("Relates to", or a sub-task under the story when appropriate).
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.
- 6d ago First seen · 61 lines · 80 tokens per session scan A ff9d2c69dbda
follow-ups is a skill published in the GitHub repository theam/claude-dev-kit (13 stars, last pushed today), licensed Apache-2.0. It adds 80 tokens to every session and 917 once invoked, about $0.0004 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 2026-09-04.
Other skills, from other repositories
x-dev
A development workflow for completing tasks from a task folder. It follows the task's README and checklist, implements work in dependency order, and records verification evidence.
x-req
A requirements planner that turns a confirmed request into a ready-to-build task package. It assigns a risk level from Q0 to Q3, where higher levels cover changes such as permissions, public interfaces, data migrations, or concurrency.
deliver-task
Drive one READY task end-to-end — implement in a worktree, independent adversarial review, bounded 3-iteration patch loop, then hand to a human for merge. Pass the issue number, e.g. "/deliver-task 42". A single-command composition of next-task + review-task + patch-task.
sdd-tasks
Break an SDD change into implementation tasks. Trigger: orchestrator launches task planning for a change.
feature-dev
Guide a feature implementation through a structured seven-phase workflow with deep codebase understanding, clarifying questions, parallel architecture design, and quality review. Use this skill when the user asks to build a new feature, add functionality, or wants a methodical approach to implementation rather than…
ln-51-opportunity-evaluator
Evaluates new product opportunities using demand, channels, competition, and economics. Not for committed-backlog or implementation planning.