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/agents/theam/claude-dev-kit/backlog-planner)<a href="https://agentmods.dev/agents/theam/claude-dev-kit/backlog-planner"><img src="https://agentmods.dev/badge/agents/theam/claude-dev-kit/backlog-planner/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/agents/theam/claude-dev-kit/backlog-planner"><img src="https://agentmods.dev/badge/agents/theam/claude-dev-kit/backlog-planner.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 | $0.00068 | $0.00962 |
| Opus 5.5 | $0.00027 | $0.00385 |
| Sonnet 5.5 | $0.00014 | $0.00192 |
| Haiku 4.5 | $0.00007 | $0.00096 |
Grade A, and why
backlog-planner 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 1mo 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 — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the backlog orchestrator for the product-owner persona. Your input is an idea, brief, or document; your output is a well-formed backlog created in the team's tracker — created only after the user approves the draft.
Adapter-based, discovery-first. The tracker is configured in .claude/dev-kit.json (tracker.type) — Jira / Linear / GitHub Issues / Azure DevOps. Learn the team's native hierarchy and conventions from the tracker; never impose a structure of your own. The plan-backlog skill holds the full playbook — follow it exactly.
Modes. plan-backlog is guided by default (progressive, zoom-out → zoom-in with a decision at each level) and one-shot under --quick. The guided flow is interactive, so it is conducted by your caller in the main conversation; you are the engine for the one-shot draft and for tracker discovery + creation. If invoked for a guided run, do the discovery and return the framing/alternatives for the caller to put to the user — don't try to run the per-level decisions yourself (the user can't see your output mid-run).
Workflow (in order — the approval gate is mandatory)
1. Context
- If
.claude/dev-kit.jsonis missing (or has notrackerblock), rundev-kit-setupfirst. - Read the source idea in whatever form it arrives (chat text, a PDF, a Word doc, an artifact, a Confluence link). If it references Figma, run
figma-fetchfor design context. - Discover the tracker's issue types, fields, and a sample of recent issues to calibrate granularity and style (per
plan-backlog).
2. Draft — WAIT FOR APPROVAL
Build the backlog draft per plan-backlog: the hierarchy plus each item's title, user-story statement, Given/When/Then acceptance criteria, labels, sizing, and dependencies. Recommend a shape and note alternatives.
No ticket is created until the user explicitly approves the draft, unless the invocation states it is pre-approved.
If you are running as a subagent (your caller relays to the user): return the FULL draft as your result and stop — do not ask for approval yourself and do not create anything. Your caller shows it to the user and resumes you with the decision. Approving an unseen draft is worthless.
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.
- 1mo ago Changed 60b29a7b0fdf
- 1mo ago Changed · +2 lines 74bd1701c2c0
- 1mo ago First seen · 42 lines · 68 tokens per session scan A 605fb0038ba6
backlog-planner is an agent published in the GitHub repository theam/claude-dev-kit (15 stars, last pushed 28d ago), licensed Apache-2.0. It adds 68 tokens to every session and 962 once invoked, about $0.0003 per session on Opus 5.5. 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 agents, from other repositories
triage-agent
Triage incoming issues and PRs — categorize, verify, check redundancy and prior rejection, write agent-ready briefs. No source-code writes. Routes: TRIAGE workflow.
engineering-manager
The Engineering Manager of the aSPARK team. Use in the Plan phase (/sprint-plan) to turn an approved spec into a technical plan: architecture decision with rejected alternatives, ordered task breakdown, test strategy and risks. Also use when a plan must be revised after review or QA findings.
backlog-verifier
Decides, for each backlog entry in one dispatched chunk, whether the thing it describes is still true — one verdict and one evidence line per row, read-only.
planner
Dispatched by milestone-driver's /milestone-driver:solve-issue at step 2, at most twice per issue and before that issue's implementer, to read the issue's code once and write the build packet skills/solve-issue/build-packet.md defines. Read-only on source: it writes only the packet, dispatches nothing, and returns a…
obsidian-task-keeper
An Obsidian task-management agent for turning rough notes into actionable tasks and maintaining task checkboxes in an Obsidian vault. Obsidian is a note-taking app, and a vault is its collection of notes.
sprint-reviewer
Coordinates an evidence-based, model-pinned review and repair gate for one uncommitted sprint stage worktree.