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/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/commands/theam/claude-dev-kit/plan-backlog)<a href="https://agentmods.dev/commands/theam/claude-dev-kit/plan-backlog"><img src="https://agentmods.dev/badge/commands/theam/claude-dev-kit/plan-backlog.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 | $0.00041 | $0.00499 |
| Opus 5 | $0.00020 | $0.00249 |
| Sonnet 5 | $0.00008 | $0.00100 |
| Haiku 4.5 | $0.00004 | $0.00050 |
Grade A, and why
plan-backlog 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 4d 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.
What it actually says
Turn the idea/brief given in the arguments into a backlog: $ARGUMENTS
Delegate to the backlog-planner subagent in two phases, passing the source (the text, or the path/URL to the document) and any extra instructions from the arguments.
Rules:
- If the arguments contain no idea or source, ask for one — do not invent scope. Accept pasted text, a path to a file (PDF / Word / Markdown), or a URL / artifact.
- The tracker is whatever
.claude/dev-kit.jsonconfigures (Jira / Linear / GitHub Issues / Azure DevOps); if it is unconfigured, the agent runsdev-kit-setupfirst.
Phase 1 — context and draft. Instruct the backlog-planner to read the source, learn the tracker's conventions, and build the backlog draft, and RETURN the full draft as its result — telling it explicitly NOT to ask for approval itself and NOT to create any tickets yet.
Approval gate — two separate steps, in this exact order:
- FIRST, print the draft: write a normal assistant message to the conversation containing the backlog-planner's FULL draft (the hierarchy plus each item's title, acceptance criteria, labels, and links), verbatim. This message is a hard requirement — a selection dialog is NOT a substitute for it, and putting the draft only inside a dialog's option text does not count: the user must be able to read the complete draft in the chat before any question appears.
- THEN, and only after that message is visible, ask the user to approve, adjust, or cancel.
Never collapse these two steps into one dialog. Only if the arguments contain --auto-approve (for automated runs), skip the gate and proceed directly.
Phase 2 — creation. On approval (or auto-approve), resume the SAME backlog-planner (so it keeps its context) with the approval and any user adjustments, and let it create the items in the tracker.
- Relay the agent's final report: each created item's key/URL, the hierarchy created, and the handoff note (each story is ready for
/work-story <KEY>).
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.
- 4d ago First seen · 26 lines · 41 tokens per session scan A 366e789bee8a
plan-backlog is a command published in the GitHub repository theam/claude-dev-kit (13 stars, last pushed yesterday), licensed Apache-2.0. It adds 41 tokens to every session and 499 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 2026-09-04.
Other commands, from other repositories
backlog
The project layer: milestones, epics, and user stories with refusing controllers — spec-seeded, sprint-ready.
sprint
Scope-boxed sprints over the backlog: one active sprint, explicit carry-over, a close that refuses to hide unfinished work.
status
The state of play, computed fresh: branch, dirty files, the active sprint, open work, index freshness.
plan
Turn an approved spec into an implementation plan an engineer with zero context could execute — with a quality controller that blocks placeholders and hollow tasks.
simplify
The over-engineering review: five tags (delete, stdlib, native, yagni, shrink), a mandatory replacement per finding, and a real null result when there is nothing to cut.
audit
Onboard an existing codebase: every domain's checks over the whole tree, then a triaged plan to bring it in line.