next

A command that reads project handoff and backlog files, then recommends one next development task. A backlog is a ranked list of unfinished work.

In plain words
What is it for?
Use it to choose the next task, understand its priority and effort, and define a test that proves the work is complete.
Why use it?
It reduces guesswork about what to work on and checks that the choice supports an active product.

Command for Claude Code

Install

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.

agentmods
npx agentmods add commands/mission69b/t2000/next
Clone the repo
git clone --depth 1 https://github.com/mission69b/t2000

Made for: Claude Code.

Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 433 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00012 $0.00433
Opus 5 $0.00006 $0.00217
Sonnet 5 $0.00002 $0.00087
Haiku 4.5 $0.00001 $0.00043

Measured 2d ago against content hash fb87b5f0ef63, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

next 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 2d 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.

.claude/commands/next.md · 41 lines

What it actually says

Figure out what to work on next.

Read these, in this order

  1. audric/HANDOFF_NEXT_AGENT.md → "Active backlog" table — this is the canonical, ranked list for product / agent-ownable tasks (with effort + notes) plus founder ops.
  2. HANDOFF_NEXT_AGENT.md (this repo) — the infra forward window and cross-repo cleanup. It defers the product backlog to the audric one, so don't treat a gap here as "nothing to do."
  3. PRODUCT.md — the product map SSOT (2 products: Private Inference · x402 gateway; one customer + one path each). Use it to sanity-check that a candidate task actually serves a live product rather than a retired surface.
  4. Top of audric-build-tracker.md — the last few S.N entries, to see what just landed and whether it left "founder ops owed" or "held for founder nod" items that are now unblocked.

All of these are local-only (gitignored, mounted from the private mission69b/t2000-internal repo at spec/).

Then

Propose one next task. For it, state:

  • What it is and which backlog row it came from.
  • Why it's next (rank, or a dependency that just cleared).
  • Rough effort.
  • The verifiable acceptance criteria — what runnable check proves it's done.
  • Which surfaces it touches (SDK / CLI / MCP / skills / docs — see /ship).

Then run the product algorithm on it before writing any code: is the requirement actually sound, and is there a version of this task that deletes something instead of adding it? Say so if there is.

Do not start implementing until the user picks. List the runner-up briefly so they can redirect in one word.

Changes

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.

  1. 2d ago First seen · 41 lines · 12 tokens per session scan A fb87b5f0ef63

Subscribe to this mod's changes

next is a command published in the GitHub repository mission69b/t2000 (23 stars, last pushed 3d ago), licensed MIT. It adds 12 tokens to every session and 433 once invoked, about $0.0001 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.